docs: the delivery A/B, and the first retrieval nobody asked for

Runs 9 and 10: identical task text, one server process, and a task that never
mentions skills, MCP or retrieval. Run 8 demonstrated the instrument, but its
retrieval was instructed by the task — it showed the pipe worked, not that an
agent would judge relevance.

Under `index`, two of four skills were fetched, and attribution is the part
that matters:

    Solveig (lead_researcher)  ->  web-search-triage
    Olamide (report_writer)    ->  scientific-writing-conventions

Each agent reached for the skill bound to its OWN role and neither reached for
another's. An agent that fetched all four would have shown only that it could.

The regression the A/B existed to catch did not appear: 34% fewer tokens, 59
tool calls against 89, both arms passed the independent judge, and the
deliverables came out slightly larger rather than thinner.

Two readings the data does not support, recorded because the first draft of
this section made one of them:

- Every `tool.call` in a phase carries the DRAIN timestamp, not the call time.
  All 59 rows of run 10 read `12:48:12`. Ordering by that column said the
  report writer had fetched both skills; `agent_id` says otherwise.
- The prompt saving is 15-43%, not an order of magnitude. Skill bodies are a
  minority of a turn prompt. Progressive disclosure is worth doing for Trigger,
  not for context economy.

`workspace-repo-commit-protocol` scores Trigger=FAIL beside boundary=pass: it
behaved correctly without reading the rule. That verdict is left standing and
argued with in the text rather than tuned away.

n=1 per arm. A signal, not a rate.

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>

crates/cm-api/src/lib.rs

@@ -54,6 +54,7 @@ pub mod security_scan;
 pub mod session_executor;
 pub mod container_tool_hooks;
 pub mod gateway_preflight;
+pub mod skill_delivery;
 pub mod skill_self_authoring;
 pub mod skill_use;
 pub mod skills_loader;

crates/cm-api/src/mcp_door.rs

@@ -237,12 +237,21 @@ async fn mint_grant(
 }
 
 /// Authenticate the bearer header → workspace/user. `None` if missing/invalid.
+///
+/// Accepts [`cm_auth::SCOPE_AGENT_DOOR`] as well as a person's session. This
+/// route is the one that can `delegate`, and the thing that will eventually
+/// hold a token for it is an agent runtime — so the narrow credential has to
+/// exist before something reaches for the only one that does.
 async fn authed(state: &AppState, headers: &HeaderMap) -> Option<cm_auth::AuthedUser> {
     let token = headers
         .get(AUTHORIZATION)
         .and_then(|v| v.to_str().ok())
         .and_then(|v| v.strip_prefix("Bearer "))?;
-    state.auth.authenticate(token).await.ok()
+    state
+        .auth
+        .authenticate_scoped(token, cm_auth::SCOPE_AGENT_DOOR)
+        .await
+        .ok()
 }
 
 /// Resolve the specific claw making the call. Our ZeroClaw fork stamps the

crates/cm-api/src/mcp_skills.rs

@@ -106,7 +106,7 @@ async fn caller_agent(
 
 // ── URI helpers ──────────────────────────────────────────────────
 
-fn skill_uri(workspace_id: Option<Uuid>, name: &str) -> String {
+pub(crate) fn skill_uri(workspace_id: Option<Uuid>, name: &str) -> String {
     match workspace_id {
         Some(ws) => format!("{URI_PREFIX_WORKSPACE}{ws}/{name}"),
         None => format!("{URI_PREFIX_GLOBAL}{name}"),

crates/cm-api/src/mission_orchestrator.rs

@@ -349,7 +349,7 @@ pub async fn on_launch(
         // Only when this mission got its OWN container — the shared runtime is
         // not ours to reconfigure, and `mission_gateway` being Some is exactly
         // the signal that `ensure_container` ran.
-        if mission_gateway.is_some() {
+        let door = if mission_gateway.is_some() {
             install_skills_door(
                 pool,
                 user_id,
@@ -357,8 +357,22 @@ pub async fn on_launch(
                 &crate::mission_runtime::container_name(mission_id),
                 p,
             )
-            .await;
-        }
+            .await
+        } else {
+            false
+        };
+        // Decided here and recorded, not re-derived per turn: this is the only
+        // point that knows whether the door actually installed, and an arm that
+        // could change mid-mission would make the run unattributable.
+        record_skill_delivery(
+            pool,
+            mission_id,
+            crate::skill_delivery::resolve(
+                crate::skill_delivery::requested_for(&mission.config),
+                door,
+            ),
+        )
+        .await;
     }
     let mut first_team_id: Option<Uuid> = None;
     let mut provisioned_claws: Vec<cm_domain::AgentId> = Vec::new();
@@ -916,19 +930,23 @@ fn default_accent_for(slot: &str) -> &'static str {
 ///
 /// Every failure degrades to "no door", never to a failed launch. A mission
 /// that cannot retrieve a skill still delivers.
+/// Returns whether the door is installed AND reachable. The caller needs the
+/// answer, not just the log line: the `index` delivery arm hands agents a list
+/// of uris to fetch, and without a door every one of them is a dead end that
+/// reads as an agent ignoring its skills.
 async fn install_skills_door(
     pool: &PgPool,
     user_id: cm_domain::UserId,
     mission_id: Uuid,
     container: &str,
     prov: &RuntimeProvisioner,
-) {
+) -> bool {
     let Some(origin) = crate::container_tool_hooks::api_origin() else {
         eprintln!(
             "mission_orchestrator: no API origin for the skills door (set \
              CLAWMATES_API_ORIGIN) — mission {mission_id} runs without it"
         );
-        return;
+        return false;
     };
     // Outlives the longest mission we have seen, and expires on its own so a
     // leaked container does not leave a live credential behind indefinitely.
@@ -943,31 +961,54 @@ async fn install_skills_door(
                 "mission_orchestrator: could not mint a skills token ({e}) — \
                  mission {mission_id} runs without the door"
             );
-            return;
+            return false;
         }
     };
     let docker = match crate::container_exec::connect() {
         Ok(d) => d,
         Err(e) => {
             eprintln!("mission_orchestrator: cannot reach docker for the skills door: {e}");
-            return;
+            return false;
         }
     };
     let doc = crate::container_tool_hooks::mcp_document(&origin, &token);
     let Some(path) = crate::container_tool_hooks::install_door(&docker, container, &doc).await
     else {
         // `install_door` already said why.
-        return;
+        return false;
     };
     if let Err(e) = prov.set_claude_cli_mcp_config(&path).await {
         eprintln!(
             "mission_orchestrator: wrote the MCP config but could not point \
              claude_cli at it ({e}) — the door is installed and unreachable"
         );
-        return;
+        return false;
     }
     eprintln!(
         "mission_orchestrator: skills door installed for mission {mission_id} \
          ({origin}/mcp/skills)"
     );
+    true
+}
+
+/// Record which arm this mission runs, so every turn composes the same one and
+/// the score can be attributed to it afterwards.
+///
+/// A write failure is not fatal: `skill_delivery_mode` reads NULL as `inline`,
+/// which is the arm that needs nothing installed. A mission that quietly ran
+/// the control arm is a lost data point; a mission that failed to launch over
+/// a telemetry column is a lost mission.
+async fn record_skill_delivery(pool: &PgPool, mission_id: Uuid, mode: crate::skill_delivery::Mode) {
+    if let Err(e) = sqlx::query("UPDATE missions SET skill_delivery = $2 WHERE id = $1")
+        .bind(mission_id)
+        .bind(mode.as_str())
+        .execute(pool)
+        .await
+    {
+        eprintln!(
+            "mission_orchestrator: could not record skill_delivery={} for mission \
+             {mission_id} ({e}) — its turns will compose skills inline",
+            mode.as_str()
+        );
+    }
 }

crates/cm-api/src/phase_runner.rs

@@ -1141,7 +1141,16 @@ async fn launch_phase(
     // `topology_exec`, with the running node's own role, and appending here too
     // would put every crew member's skills in every turn twice.
     let task_with_skills = match phase_skills_text(pool, mission_id).await {
-        Some(skills) => crate::topology_exec::compose_turn_prompt(&task, Some(&skills)),
+        // Always `Inline` here, and not because it is the default: the solo
+        // tiers get no skills door (`install_skills_door` runs only for a
+        // mission with its own container), so an index would list uris nothing
+        // in the VM can fetch. When the microVM tier folds onto
+        // `container_tool_hooks` this becomes a real choice; today it is a fact.
+        Some(skills) => crate::topology_exec::compose_turn_prompt(
+            &task,
+            Some(&skills),
+            crate::skill_delivery::Mode::Inline,
+        ),
         None => task.clone(),
     };
 

crates/cm-api/src/skill_delivery.rs

@@ -0,0 +1,255 @@
+//! How a mission agent receives the skills bound to it.
+//!
+//! Two arms, and this module exists to hold them side by side rather than to
+//! replace one with the other:
+//!
+//! - [`Mode::Inline`] — every pinned skill's full body is appended to the turn
+//!   prompt. What production has always done.
+//! - [`Mode::Index`] — the prompt carries each skill's name, description and
+//!   `when_to_use` plus the URI that returns its body, and the agent fetches
+//!   the ones it judges relevant.
+//!
+//! # Why this is an A/B and not a switch
+//!
+//! Trigger — did the agent reach for the skill when it applied? — is
+//! unmeasurable under `Inline` by construction. Nothing was reached for; the
+//! text was handed over. `skill_use` reports `NotObservable` for exactly that
+//! reason, and it is right to.
+//!
+//! `Index` makes Trigger observable, because retrieval is a recorded
+//! `ReadMcpResourceTool` call. But it can only *cost* Compliance: under
+//! `Inline` the procedure is in front of the model whether or not it noticed
+//! it applied, and under `Index` a missed judgement means the body is never
+//! read at all. Trading a measured axis for an unmeasured regression in
+//! another is not an improvement, so the arm is selected per mission and
+//! recorded on the mission row, and both arms stay runnable.
+//!
+//! # `Index` requires the door, and degrades rather than lying
+//!
+//! An index names a body and tells the agent how to fetch it. If the
+//! `clawmates_skills` MCP server is not reachable from the container, that is
+//! an index of procedures the agent cannot obtain — strictly worse than
+//! `Inline`, and it fails as an agent that ignored its skills rather than as a
+//! missing config. [`resolve`] therefore takes the door's install result and
+//! refuses `Index` without it. This is the same failure the old
+//! `pinned_skills_text` doc comment warned about; what changed is that the
+//! door now exists, not that the warning stopped applying.
+
+/// Where the index tells agents to fetch a skill body from.
+///
+/// Must match the server name in
+/// [`crate::container_tool_hooks::mcp_document`] — the agent passes it
+/// straight to `ReadMcpResourceTool`.
+pub const MCP_SERVER: &str = "clawmates_skills";
+
+/// Selects the arm. Unset or unrecognised means [`Mode::Inline`].
+pub const ENV_VAR: &str = "CLAWMATES_SKILL_DELIVERY";
+
+/// The `# Your skills` preamble under [`Mode::Inline`].
+///
+/// **Byte-identical to what production has always sent.** The A arm of an A/B
+/// has to be the thing already running, or the comparison measures this edit
+/// as well as the change under test.
+pub const INLINE_PREAMBLE: &str = "These are procedures you are expected to follow for \
+this kind of work. Where one applies to what you are about to do, follow it.";
+
+/// The `# Your skills` preamble under [`Mode::Index`].
+///
+/// Written and matched in one place ([`mode_in_prompt`]) so the reader cannot
+/// drift from the writer — the same rule `SKILL_MARKER` is under, and for the
+/// same reason: a scorer that misreads the arm reports the wrong axis.
+pub const INDEX_PREAMBLE: &str = "These procedures are AVAILABLE to you; their bodies are \
+not included below. Each entry names one, says when it applies, and gives the uri that \
+returns it. Where an entry applies to what you are about to do, read it FIRST and then \
+follow it.";
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum Mode {
+    Inline,
+    Index,
+}
+
+impl Mode {
+    pub fn as_str(self) -> &'static str {
+        match self {
+            Mode::Inline => "inline",
+            Mode::Index => "index",
+        }
+    }
+}
+
+/// Parse a recorded or configured arm. Unrecognised input is `None`, and every
+/// caller resolves that to `Inline` — an unreadable value must not silently
+/// select the arm that needs a door.
+pub fn parse(s: &str) -> Option<Mode> {
+    match s.trim().to_ascii_lowercase().as_str() {
+        "inline" => Some(Mode::Inline),
+        "index" | "progressive" => Some(Mode::Index),
+        _ => None,
+    }
+}
+
+/// The arm this deployment asks for, before the door is taken into account.
+pub fn requested() -> Mode {
+    let Ok(raw) = std::env::var(ENV_VAR) else {
+        return Mode::Inline;
+    };
+    if raw.trim().is_empty() {
+        return Mode::Inline;
+    }
+    match parse(&raw) {
+        Some(m) => m,
+        None => {
+            eprintln!(
+                "skill_delivery: {ENV_VAR}={raw:?} is not `inline` or `index` — \
+                 delivering skills inline"
+            );
+            Mode::Inline
+        }
+    }
+}
+
+/// The arm for one mission: `config.skill_delivery` if it names one, otherwise
+/// the deployment default.
+///
+/// Per-mission and not only per-deployment because the alternative is
+/// restarting the server between arms, and an A/B whose two halves ran against
+/// different server processes has a confound in it that nothing in the numbers
+/// will show. This way both arms run against one binary, interleaved.
+pub fn requested_for(config: &serde_json::Value) -> Mode {
+    let Some(raw) = config.get("skill_delivery").and_then(|v| v.as_str()) else {
+        return requested();
+    };
+    match parse(raw) {
+        Some(m) => m,
+        None => {
+            eprintln!(
+                "skill_delivery: config.skill_delivery={raw:?} is not `inline` or \
+                 `index` — falling back to the deployment default"
+            );
+            requested()
+        }
+    }
+}
+
+/// The arm a mission will actually run, given whether its skills door installed.
+pub fn resolve(requested: Mode, door_installed: bool) -> Mode {
+    match (requested, door_installed) {
+        (Mode::Index, true) => Mode::Index,
+        (Mode::Index, false) => {
+            eprintln!(
+                "skill_delivery: {ENV_VAR} asked for `index` but this mission has no \
+                 skills door — falling back to `inline`, because an index the agent \
+                 cannot fetch from is worse than no index"
+            );
+            Mode::Inline
+        }
+        (Mode::Inline, _) => Mode::Inline,
+    }
+}
+
+/// The `# Your skills` section heading for an arm.
+pub fn preamble(mode: Mode) -> &'static str {
+    match mode {
+        Mode::Inline => INLINE_PREAMBLE,
+        Mode::Index => INDEX_PREAMBLE,
+    }
+}
+
+/// Which arm produced a recorded prompt.
+///
+/// Read back from the prompt rather than from the mission row on purpose: the
+/// row says what the mission was configured to do *now*, and a score is being
+/// computed against a prompt that was composed then. The recorded prompt is
+/// the only artefact that cannot have changed since the turn ran.
+///
+/// Matched as a whole line. A skill body that quotes the preamble mid-sentence
+/// is prose; this is the same rule `skill_names_in` learned the hard way.
+pub fn mode_in_prompt(prompt: &str) -> Mode {
+    if prompt.lines().any(|l| l.trim() == INDEX_PREAMBLE) {
+        Mode::Index
+    } else {
+        Mode::Inline
+    }
+}
+
+/// One index entry's text — everything under the `--- SKILL: <name> ---`
+/// marker, which [`crate::topology_exec::render_pinned_skill`] writes.
+///
+/// `when_to_use` is the load-bearing field: it is the only thing the agent has
+/// to judge relevance from, so a skill with none says so rather than omitting
+/// the line and leaving the model to infer from the description alone.
+pub fn index_entry(description: &str, when_to_use: Option<&str>, uri: &str) -> String {
+    let when = when_to_use
+        .map(str::trim)
+        .filter(|w| !w.is_empty())
+        .unwrap_or("not stated — judge from the description");
+    format!(
+        "{}\nWhen to use: {}\nRead it: ReadMcpResourceTool(server=\"{}\", uri=\"{}\")",
+        description.trim(),
+        when,
+        MCP_SERVER,
+        uri,
+    )
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn an_unreadable_arm_never_selects_the_one_that_needs_a_door() {
+        assert_eq!(parse("nonsense"), None);
+        assert_eq!(parse("INDEX"), Some(Mode::Index));
+        assert_eq!(parse(" inline "), Some(Mode::Inline));
+    }
+
+    #[test]
+    fn a_mission_can_name_its_own_arm() {
+        assert_eq!(
+            requested_for(&serde_json::json!({ "skill_delivery": "index" })),
+            Mode::Index
+        );
+        // Unreadable values and absent ones both defer to the deployment
+        // default, which is `Inline` unless the environment says otherwise.
+        assert_eq!(
+            requested_for(&serde_json::json!({ "skill_delivery": "sideways" })),
+            requested()
+        );
+        assert_eq!(requested_for(&serde_json::json!({})), requested());
+    }
+
+    #[test]
+    fn index_without_a_door_falls_back() {
+        assert_eq!(resolve(Mode::Index, false), Mode::Inline);
+        assert_eq!(resolve(Mode::Index, true), Mode::Index);
+        assert_eq!(resolve(Mode::Inline, true), Mode::Inline);
+    }
+
+    /// The scorer reads the arm off the prompt, so the writer and this reader
+    /// have to agree for every arm — including the one that writes no marker.
+    #[test]
+    fn the_arm_is_recoverable_from_the_prompt_that_was_sent() {
+        let inline = format!("Task: x\n\n# Your skills\n\n{INLINE_PREAMBLE}\n\nbody");
+        let index = format!("Task: x\n\n# Your skills\n\n{INDEX_PREAMBLE}\n\nentry");
+        assert_eq!(mode_in_prompt(&inline), Mode::Inline);
+        assert_eq!(mode_in_prompt(&index), Mode::Index);
+        assert_eq!(mode_in_prompt("Task: x"), Mode::Inline);
+    }
+
+    /// A body quoting the preamble must not re-label the arm — the same
+    /// failure `SKILL_MARKER` had when a heading inside a body counted.
+    #[test]
+    fn a_body_quoting_the_preamble_does_not_change_the_arm() {
+        let body = format!("The index arm opens with \"{INDEX_PREAMBLE}\" and then lists.");
+        let prompt = format!("Task: x\n\n# Your skills\n\n{INLINE_PREAMBLE}\n\n{body}");
+        assert_eq!(mode_in_prompt(&prompt), Mode::Inline);
+    }
+
+    #[test]
+    fn an_entry_states_a_missing_when_to_use_rather_than_dropping_the_line() {
+        let e = index_entry("Summarise a paper.", None, "skill:global/x");
+        assert!(e.contains("When to use: not stated"), "{e}");
+        assert!(e.contains("ReadMcpResourceTool(server=\"clawmates_skills\""), "{e}");
+    }
+}

crates/cm-api/src/skill_use.rs

@@ -189,6 +189,55 @@ pub fn retrieved_skills(ev: &Evidence<'_>) -> Vec<String> {
     out
 }
 
+/// Did the agent reach for this skill?
+///
+/// The answer depends on whether it was ever given the chance, which is what
+/// the delivery arm decides — so this takes the arm rather than assuming one.
+/// Getting that wrong is not a rounding error: under `Index` the old text
+/// would have said "this skill was inlined into the prompt" about a skill that
+/// was not, and scored a real miss as a structural blind spot.
+fn trigger_verdict(
+    mode: crate::skill_delivery::Mode,
+    retrieved: bool,
+    compliance: &Verdict,
+    boundary: &Verdict,
+) -> Verdict {
+    if retrieved {
+        // The agent reached for it. That is the paper's Trigger, and it is a
+        // recorded tool call like any other.
+        return Verdict::Pass;
+    }
+    match mode {
+        // Handed over, so there was no reaching-for to observe. Not a failure
+        // and not a pass — the axis simply does not exist in this arm.
+        crate::skill_delivery::Mode::Inline => Verdict::NotObservable(
+            "this skill was inlined into the prompt, not retrieved — the agent \
+             was handed it, so there is no reaching-for to observe. Serve it \
+             through the door instead and this becomes a tool call"
+                .into(),
+        ),
+        crate::skill_delivery::Mode::Index => {
+            // Offered by name and `when_to_use`, and never opened. Whether that
+            // is a miss depends on whether the skill had anything to say about
+            // this phase at all: a skill with no machine-checkable consequence
+            // here is one an agent is right to pass over, and scoring that as a
+            // failure would punish correct triage.
+            if matches!(compliance, Verdict::NotApplicable)
+                && matches!(boundary, Verdict::NotApplicable)
+            {
+                Verdict::NotApplicable
+            } else {
+                Verdict::Fail(
+                    "offered in the index with its `when_to_use`, and never read — \
+                     the agent had the entry in front of it and did not fetch the \
+                     procedure"
+                        .into(),
+                )
+            }
+        }
+    }
+}
+
 /// Score every skill a phase's prompt delivered, against what the agent produced.
 pub fn score(
     prompt: &str,
@@ -196,6 +245,10 @@ pub fn score(
     source_kinds: &dyn Fn(&str) -> String,
 ) -> Vec<SkillUse> {
     let retrieved = retrieved_skills(evidence);
+    // Read off the prompt that was actually sent, not off the mission row: the
+    // row says what the mission is configured to do now, and this is scoring a
+    // turn that ran then.
+    let mode = crate::skill_delivery::mode_in_prompt(prompt);
     // Delivered by either route. A skill that was retrieved and never inlined
     // is invisible to `skills_in_prompt`, and under progressive disclosure that
     // is EVERY skill — so scoring only the prompt would report zero for the
@@ -212,19 +265,12 @@ pub fn score(
             let (compliance, boundary) = check(&skill, evidence);
             SkillUse {
                 source_kind: source_kinds(&skill),
-                trigger: if retrieved.contains(&skill) {
-                    // The agent reached for it. That is the paper's Trigger,
-                    // and it is now a recorded tool call like any other.
-                    Verdict::Pass
-                } else {
-                    Verdict::NotObservable(
-                        "this skill was inlined into the prompt, not retrieved — \
-                         the agent was handed it, so there is no reaching-for to \
-                         observe. Serve it through the door instead and this \
-                         becomes a tool call"
-                            .into(),
-                    )
-                },
+                trigger: trigger_verdict(
+                    mode,
+                    retrieved.contains(&skill),
+                    &compliance,
+                    &boundary,
+                ),
                 compliance,
                 boundary,
                 skill,
@@ -855,7 +901,122 @@ mod tests {
             .iter()
             .map(|(n, b)| crate::topology_exec::render_pinned_skill(n, b))
             .collect();
-        crate::topology_exec::compose_turn_prompt("Task: do the thing", Some(&body))
+        crate::topology_exec::compose_turn_prompt(
+            "Task: do the thing",
+            Some(&body),
+            crate::skill_delivery::Mode::Inline,
+        )
+    }
+
+    /// A prompt as the delivery layer renders it under the INDEX arm.
+    fn rendered_index(skills: &[(&str, &str)]) -> String {
+        let body: String = skills
+            .iter()
+            .map(|(name, when)| {
+                crate::topology_exec::render_pinned_skill(
+                    name,
+                    &crate::skill_delivery::index_entry(
+                        "a procedure",
+                        Some(when),
+                        &format!("skill:global/{name}"),
+                    ),
+                )
+            })
+            .collect();
+        crate::topology_exec::compose_turn_prompt(
+            "Task: do the thing",
+            Some(&body),
+            crate::skill_delivery::Mode::Index,
+        )
+    }
+
+    fn read_skill(uri: &str) -> ToolEvidence {
+        ToolEvidence {
+            tool: "ReadMcpResourceTool".into(),
+            path: None,
+            input: json!({ "server": "clawmates_skills", "uri": uri }),
+            response: serde_json::Value::Null,
+        }
+    }
+
+    /// The whole loop, end to end: the index writes a uri, the agent reads that
+    /// exact uri back, and the scorer recovers the skill's name from it.
+    ///
+    /// Three components have to agree on one string — `mcp_skills::skill_uri`
+    /// writes it, `skill_delivery::index_entry` puts it in the prompt, and
+    /// `parse_uri` reads it. Asserting them separately would let any pair drift
+    /// while each one's own test stayed green.
+    #[test]
+    fn the_uri_the_index_advertises_is_the_one_the_scorer_recovers() {
+        let prompt = rendered_index(&[("workspace-repo-commit-protocol", "before committing")]);
+        assert!(
+            prompt.contains("uri=\"skill:global/workspace-repo-commit-protocol\""),
+            "the entry must name the uri to fetch:\n{prompt}"
+        );
+        let tools = vec![read_skill("skill:global/workspace-repo-commit-protocol")];
+        let ev = Evidence::new("", &tools);
+        assert_eq!(
+            retrieved_skills(&ev),
+            vec!["workspace-repo-commit-protocol"],
+            "the uri the prompt advertised must parse back to the skill's name"
+        );
+        let scored = score(&prompt, &ev, &builtin);
+        assert_eq!(scored.len(), 1);
+        assert!(
+            matches!(scored[0].trigger, Verdict::Pass),
+            "reaching for an indexed skill IS the Trigger axis: {:?}",
+            scored[0].trigger
+        );
+    }
+
+    /// The index arm must not report a miss as a blind spot.
+    ///
+    /// Under `Inline` "never retrieved" is `NotObservable`, and that is honest
+    /// there. Reusing it here would say "this skill was inlined into the
+    /// prompt" about a skill whose body was never sent — the exact shape of a
+    /// check reporting a system defect where an agent behaviour belongs.
+    #[test]
+    fn an_indexed_skill_that_was_never_read_is_a_miss_not_a_blind_spot() {
+        let prompt = rendered_index(&[("workspace-repo-commit-protocol", "before committing")]);
+        // It wrote outside the mission checkout, so the boundary check applies
+        // — this skill had something to say about this phase and went unread.
+        let tools = acted(&[("Write", Some("/tmp/scratch.rs"), json!({}))]);
+        let scored = score(&prompt, &Evidence::new("", &tools), &builtin);
+        assert!(
+            matches!(scored[0].trigger, Verdict::Fail(_)),
+            "offered by name and when_to_use, never fetched: {:?}",
+            scored[0].trigger
+        );
+    }
+
+    /// ...but only when the skill had a consequence to check.
+    ///
+    /// A skill with nothing machine-checkable in this phase is one an agent is
+    /// right to pass over, and scoring that as a Trigger failure would punish
+    /// correct triage — which is the behaviour progressive disclosure is
+    /// supposed to reward.
+    #[test]
+    fn passing_over_a_skill_with_nothing_to_check_is_not_a_trigger_failure() {
+        let prompt = rendered_index(&[("some-unchecked-skill", "when writing prose")]);
+        let scored = score(&prompt, &narrative("wrote the report"), &builtin);
+        assert!(
+            matches!(scored[0].trigger, Verdict::NotApplicable),
+            "{:?}",
+            scored[0].trigger
+        );
+    }
+
+    /// The control arm has to be unchanged, or the A/B measures this edit too.
+    #[test]
+    fn the_inline_arm_still_reports_trigger_as_unobservable() {
+        let prompt = rendered(&[("workspace-repo-commit-protocol", "body")]);
+        let tools = acted(&[("Write", Some("/tmp/scratch.rs"), json!({}))]);
+        let scored = score(&prompt, &Evidence::new("", &tools), &builtin);
+        assert!(
+            matches!(scored[0].trigger, Verdict::NotObservable(_)),
+            "{:?}",
+            scored[0].trigger
+        );
     }
 
     /// The prompt is the record of what was delivered, so parsing it must match

crates/cm-api/src/topology_exec.rs

@@ -337,12 +337,50 @@ impl ZeroClawDriveExecutor {
     /// for a mission role was unreachable prose, and no measurement of whether
     /// skills fire could have returned anything but zero.
     ///
-    /// Bodies, not an index. The chat path lists names and lets the claw call
-    /// `skills.read`; there is no such tool here, so an index would advertise a
-    /// capability that does not exist — the exact failure this whole change is
-    /// about. Pinned only (`pin_in_context`), because everything else would go
-    /// in unbounded and unread.
+    /// Bodies or an index, depending on the mission's arm — see
+    /// [`crate::skill_delivery`]. Bodies were once the only honest option:
+    /// there was no tool on the mission path that could fetch one, so an index
+    /// would have advertised a capability that did not exist. The skills door
+    /// changed that, and the arm is now recorded per mission so both can run.
+    ///
+    /// Pinned only (`pin_in_context`) in either arm, because everything else
+    /// would go in unbounded and unread.
     pub async fn pinned_skills_text(&self, alias: &str) -> Option<String> {
+        let mode = self.skill_delivery_mode().await;
+        self.pinned_skills_in_mode(alias, mode).await
+    }
+
+    /// The arm this mission was launched with.
+    ///
+    /// Read per turn rather than cached on the executor: the executor is
+    /// constructed from the environment by `topology_worker`, which knows
+    /// nothing about a mission, and the arm is decided at launch by the code
+    /// that also learns whether the door installed.
+    ///
+    /// Anything unreadable — no tap, no row, an unrecognised value — resolves
+    /// to `Inline`, which is the arm that needs nothing to be true.
+    pub(crate) async fn skill_delivery_mode(&self) -> crate::skill_delivery::Mode {
+        let Some(tap) = self.tap.as_ref() else {
+            return crate::skill_delivery::Mode::Inline;
+        };
+        sqlx::query_scalar::<_, Option<String>>(
+            "SELECT skill_delivery FROM missions WHERE id = $1",
+        )
+        .bind(tap.mission_id)
+        .fetch_optional(&tap.pool)
+        .await
+        .ok()
+        .flatten()
+        .flatten()
+        .and_then(|s| crate::skill_delivery::parse(&s))
+        .unwrap_or(crate::skill_delivery::Mode::Inline)
+    }
+
+    pub(crate) async fn pinned_skills_in_mode(
+        &self,
+        alias: &str,
+        mode: crate::skill_delivery::Mode,
+    ) -> Option<String> {
         let tap = self.tap.as_ref()?;
         let agent_id = crate::runtime_provision::claw_from_alias(alias)?;
         let link = cm_db::repo::agent_template_link::get(&tap.pool, agent_id)
@@ -361,17 +399,29 @@ impl ZeroClawDriveExecutor {
         let mut out = String::new();
         let mut n = 0usize;
         for b in bindings.iter().filter(|b| b.pin_in_context) {
+            let text = match mode {
+                crate::skill_delivery::Mode::Inline => b.skill.body.clone(),
+                // An entry is a few hundred bytes whatever the body weighs, so
+                // the index arm cannot hit the cap that follows. That is the
+                // point of it, and the reason the cap is checked against the
+                // rendered text rather than against the body.
+                crate::skill_delivery::Mode::Index => crate::skill_delivery::index_entry(
+                    &b.skill.description,
+                    b.skill.when_to_use.as_deref(),
+                    &crate::mcp_skills::skill_uri(b.skill.workspace_id, &b.skill.name),
+                ),
+            };
             // Bounded, and truncation is STATED. A silently clipped procedure
             // is worse than an absent one: the agent follows the half it can
             // see and reports success against a rule it never read.
-            if out.len() + b.skill.body.len() > MAX_PINNED_SKILL_BYTES {
+            if out.len() + text.len() > MAX_PINNED_SKILL_BYTES {
                 out.push_str(&format!(
                     "\n[skill \"{}\" omitted — the pinned set exceeded {} bytes]\n",
                     b.skill.name, MAX_PINNED_SKILL_BYTES
                 ));
                 continue;
             }
-            out.push_str(&render_pinned_skill(&b.skill.name, &b.skill.body));
+            out.push_str(&render_pinned_skill(&b.skill.name, &text));
             n += 1;
         }
         if n == 0 {
@@ -778,9 +828,14 @@ impl TurnExecutor for ZeroClawDriveExecutor {
                 );
                 fallback
             });
+        // One lookup, used for the section, its preamble and the record.
+        // Deriving it three times would let a mission compose an index under
+        // an inline heading if the row changed mid-run.
+        let mode = self.skill_delivery_mode().await;
         let prompt = compose_turn_prompt(
             &Self::build_prompt(&req),
-            self.pinned_skills_text(&alias).await.as_deref(),
+            self.pinned_skills_in_mode(&alias, mode).await.as_deref(),
+            mode,
         );
         // Record what this agent is ACTUALLY about to receive, before driving.
         // Re-deriving it later would re-run the skill lookup against a
@@ -795,7 +850,14 @@ impl TurnExecutor for ZeroClawDriveExecutor {
             ev.run_id = tap.run_id;
             ev.agent_id = crate::runtime_provision::claw_from_alias(&alias);
             ev.target = Some(req.role.clone());
-            ev.detail = serde_json::json!({ "text": prompt, "tier": "container" });
+            ev.detail = serde_json::json!({
+                "text": prompt,
+                "tier": "container",
+                // The A/B arm, alongside the prompt it produced. `skill_use`
+                // recovers this from the prompt text itself, so this field is
+                // for reporting and for catching the two disagreeing.
+                "skill_delivery": mode.as_str(),
+            });
             crate::mission_events::record(&tap.pool, ev).await;
         }
         self.drive(&alias, &prompt).await
@@ -807,17 +869,22 @@ impl TurnExecutor for ZeroClawDriveExecutor {
 /// Split out from `run_turn` so the wiring is testable: `pinned_skills_text`
 /// working and `run_turn` actually calling it are different claims, and the
 /// second is the one that was false for every skill in the catalogue.
-pub fn compose_turn_prompt(base: &str, skills: Option<&str>) -> String {
+pub fn compose_turn_prompt(
+    base: &str,
+    skills: Option<&str>,
+    mode: crate::skill_delivery::Mode,
+) -> String {
     let Some(skills) = skills.map(str::trim).filter(|s| !s.is_empty()) else {
         // No heading when there is nothing under it. An empty "Your skills"
         // section tells the model it has skills and then shows it none, which
         // is worse than silence.
         return base.to_string();
     };
-    format!(
-        "{base}\n\n# Your skills\n\nThese are procedures you are expected to follow for \
-         this kind of work. Where one applies to what you are about to do, follow it.\n\n{skills}"
-    )
+    // The preamble differs per arm and lives in `skill_delivery`, because it
+    // is also what the scorer reads the arm back from. Two copies of this
+    // sentence is two chances for the reader to stop recognising the writer.
+    let preamble = crate::skill_delivery::preamble(mode);
+    format!("{base}\n\n# Your skills\n\n{preamble}\n\n{skills}")
 }
 
 /// Parse `role=alias,role=alias` into a map (blank/malformed entries skipped).

crates/cm-api/tests/mission_skill_delivery.rs

@@ -10,6 +10,7 @@
 //! structurally unreadable. That is why this is a test and not a comment: the
 //! failure produced no error anywhere, and every layer reported success.
 
+use cm_api::skill_delivery::Mode;
 use cm_api::topology_exec::{MissionTap, ZeroClawDriveExecutor};
 use cm_domain::{Agent, AgentId, AgentStatus, Role, User, UserId, Workspace, WorkspaceId};
 
@@ -121,6 +122,14 @@ async fn seed_claw_with_pinned_skill(pool: &sqlx::PgPool, body: &str) -> (String
 }
 
 fn executor(pool: &sqlx::PgPool, workspace_id: WorkspaceId) -> ZeroClawDriveExecutor {
+    executor_for(pool, workspace_id, Uuid::now_v7())
+}
+
+fn executor_for(
+    pool: &sqlx::PgPool,
+    workspace_id: WorkspaceId,
+    mission_id: Uuid,
+) -> ZeroClawDriveExecutor {
     ZeroClawDriveExecutor::new(
         "http://127.0.0.1:1".into(),
         "unused".into(),
@@ -130,12 +139,93 @@ fn executor(pool: &sqlx::PgPool, workspace_id: WorkspaceId) -> ZeroClawDriveExec
     .with_tap(MissionTap {
         pool: pool.clone(),
         workspace_id: workspace_id.as_uuid(),
-        mission_id: Uuid::now_v7(),
+        mission_id,
         phase_id: None,
         run_id: None,
     })
 }
 
+/// A mission row carrying an explicit delivery arm.
+async fn seed_mission_on_arm(pool: &sqlx::PgPool, ws: WorkspaceId, arm: Option<&str>) -> Uuid {
+    let mission = Uuid::now_v7();
+    sqlx::query(
+        "INSERT INTO missions (id, workspace_id, title, template_kind, status, skill_delivery)
+         VALUES ($1, $2, 'arm', 'research_only', 'running', $3)",
+    )
+    .bind(mission)
+    .bind(ws.as_uuid())
+    .bind(arm)
+    .execute(pool)
+    .await
+    .unwrap();
+    mission
+}
+
+// ── The index arm ───────────────────────────────────────────────────
+//
+// Trigger — did the agent reach for the skill? — cannot exist while every body
+// is handed over unasked. These tests cover the arm that makes it a question,
+// and the one guarantee the control arm needs: that it did not change.
+
+#[tokio::test]
+async fn the_index_arm_sends_the_uri_and_withholds_the_body() {
+    let pool = cm_testkit::test_pool().await;
+    const MARKER: &str = "Never review a paper from its title alone.";
+    let (alias, ws) = seed_claw_with_pinned_skill(&pool, MARKER).await;
+    let mission = seed_mission_on_arm(&pool, ws, Some("index")).await;
+
+    let text = executor_for(&pool, ws, mission)
+        .pinned_skills_text(&alias)
+        .await
+        .expect("an indexed skill is still delivered — as an entry, not a body");
+
+    assert!(
+        !text.contains(MARKER),
+        "the BODY is what the index withholds; leaving it in delivers both \
+         arms at once and measures neither. Got:\n{text}"
+    );
+    assert!(
+        text.contains("uri=\"skill:global/delivery-test-skill-"),
+        "an entry without a fetchable uri names a procedure the agent cannot \
+         obtain — worse than inlining it. Got:\n{text}"
+    );
+    assert!(
+        text.contains("When to use: always"),
+        "`when_to_use` is the only thing the agent can judge relevance from, \
+         and judging relevance is the entire axis. Got:\n{text}"
+    );
+    // The scorer counts delivered skills by the marker, in both arms.
+    assert_eq!(
+        cm_api::topology_exec::skill_names_in(&text).len(),
+        1,
+        "an indexed skill must still count as delivered:\n{text}"
+    );
+}
+
+#[tokio::test]
+async fn an_unrecorded_arm_delivers_bodies() {
+    let pool = cm_testkit::test_pool().await;
+    const MARKER: &str = "Never review a paper from its title alone.";
+    let (alias, ws) = seed_claw_with_pinned_skill(&pool, MARKER).await;
+
+    // Every mission that ran before the column existed, plus any row whose
+    // value is unreadable, plus a turn with no mission row at all. All three
+    // resolve to the arm that needs nothing installed to work.
+    for arm in [None, Some("nonsense")] {
+        let mission = seed_mission_on_arm(&pool, ws, arm).await;
+        let text = executor_for(&pool, ws, mission)
+            .pinned_skills_text(&alias)
+            .await
+            .unwrap();
+        assert!(
+            text.contains(MARKER),
+            "skill_delivery={arm:?} must deliver the body — an index arm \
+             selected by accident hands out uris behind a door that may not \
+             be installed. Got:\n{text}"
+        );
+    }
+}
+
 #[tokio::test]
 async fn a_pinned_skill_body_reaches_the_turn_prompt() {
     let pool = cm_testkit::test_pool().await;
@@ -149,9 +239,9 @@ async fn a_pinned_skill_body_reaches_the_turn_prompt() {
 
     assert!(
         text.contains(MARKER),
-        "the skill BODY must be present, not just its name — there is no \
-         `skills.read` tool on the mission path, so an index would name a \
-         procedure the agent has no way to fetch. Got:\n{text}"
+        "the default arm delivers the BODY. It is the control in the delivery \
+         A/B, so it has to stay what production has always sent; the index arm \
+         is selected per mission and tested separately. Got:\n{text}"
     );
 }
 
@@ -197,13 +287,13 @@ async fn an_agent_with_no_pinned_skills_adds_nothing() {
 fn the_composed_prompt_carries_the_skill_and_omits_the_heading_when_empty() {
     let base = "You are the \"researcher\" agent.\n\nTask: read the papers";
 
-    let with = cm_api::topology_exec::compose_turn_prompt(base, Some("## arxiv-daily\nDo not re-search."));
+    let with = cm_api::topology_exec::compose_turn_prompt(base, Some("## arxiv-daily\nDo not re-search."), Mode::Inline);
     assert!(with.contains("Task: read the papers"), "the base turn must survive");
     assert!(with.contains("Do not re-search."), "the skill body must be in the prompt");
     assert!(with.contains("# Your skills"), "the section needs a heading");
 
     for empty in [None, Some(""), Some("   \n ")] {
-        let without = cm_api::topology_exec::compose_turn_prompt(base, empty);
+        let without = cm_api::topology_exec::compose_turn_prompt(base, empty, Mode::Inline);
         assert_eq!(
             without, base,
             "with no skills the prompt must be byte-identical to the base — an \
@@ -277,7 +367,7 @@ async fn the_microvm_and_session_tiers_get_the_skill_in_their_task_text() {
     );
 
     // All three tiers share this composition, so testing it once covers them.
-    let composed = cm_api::topology_exec::compose_turn_prompt("Task: read the papers", Some(&skills));
+    let composed = cm_api::topology_exec::compose_turn_prompt("Task: read the papers", Some(&skills), Mode::Inline);
     assert!(composed.contains(MARKER));
     assert!(composed.contains("Task: read the papers"));
 }

crates/cm-auth/src/lib.rs

@@ -13,6 +13,7 @@ mod token;
 pub use bootstrap::bootstrap_owner;
 pub use jwt::{ExternalClaims, JwtError, JwtVerifier};
 pub use service::{
-    AuthError, AuthService, AuthedUser, SCOPE_FULL, SCOPE_SKILLS_READ, SESSION_TTL,
+    AuthError, AuthService, AuthedUser, SCOPE_AGENT_DOOR, SCOPE_FULL, SCOPE_SKILLS_READ,
+    SESSION_TTL,
 };
 pub use token::SessionToken;

crates/cm-auth/src/service.rs

@@ -21,6 +21,19 @@ pub const SCOPE_FULL: &str = "full";
 /// that authenticates nowhere, which fails safely but silently.
 pub const SCOPE_SKILLS_READ: &str = "skills:read";
 
+/// Act through the §15 MCP door (`/mcp`), and nothing else.
+///
+/// The door is the actuator: `email_send`, `slack_post`, `delegate`. Reaching
+/// it means a token an agent's runtime holds, and the same reasoning as
+/// [`SCOPE_SKILLS_READ`] applies — a full session there is an owner-privileged
+/// API key handed to a process whose whole purpose is to act on instructions
+/// from a model.
+///
+/// Nothing mints one yet; the route accepts it so that whatever does will not
+/// have to reach for a person's session to be understood. `full` still works,
+/// so the UI and any human caller are unaffected.
+pub const SCOPE_AGENT_DOOR: &str = "agent:door";
+
 /// The authenticated caller attached to every API request: everything RBAC
 /// decisions need, nothing more.
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]

crates/cm-auth/tests/local_auth.rs

@@ -168,6 +168,54 @@ async fn a_scoped_token_is_refused_by_every_unscoped_caller() {
     assert_eq!(ok.user_id, user.id);
 }
 
+/// The two narrow scopes must not substitute for each other.
+///
+/// They protect different things — one reads the skills catalogue, the other
+/// operates the §15 door that can `delegate`. Both tokens live where an agent
+/// can read them, so the whole value of having two constants is that holding
+/// one grants nothing the other has.
+#[tokio::test]
+async fn one_narrow_scope_does_not_open_the_other() {
+    let pool = cm_testkit::test_pool().await;
+    let (_ws, user) = seeded(&pool).await;
+    let auth = AuthService::new(pool);
+
+    let skills = auth
+        .mint_scoped(user.id, cm_auth::SCOPE_SKILLS_READ, time::Duration::hours(1))
+        .await
+        .unwrap();
+    let door = auth
+        .mint_scoped(user.id, cm_auth::SCOPE_AGENT_DOOR, time::Duration::hours(1))
+        .await
+        .unwrap();
+
+    assert!(
+        matches!(
+            auth.authenticate_scoped(&skills, cm_auth::SCOPE_AGENT_DOOR).await,
+            Err(AuthError::Unauthenticated)
+        ),
+        "a skills token must not reach the door — the door can `delegate`"
+    );
+    assert!(
+        matches!(
+            auth.authenticate_scoped(&door, cm_auth::SCOPE_SKILLS_READ).await,
+            Err(AuthError::Unauthenticated)
+        ),
+        "and a door token must not read the catalogue"
+    );
+    assert!(
+        matches!(
+            auth.authenticate(&door).await,
+            Err(AuthError::Unauthenticated)
+        ),
+        "nor authenticate an ordinary API call"
+    );
+    assert!(auth
+        .authenticate_scoped(&door, cm_auth::SCOPE_AGENT_DOOR)
+        .await
+        .is_ok());
+}
+
 /// A person's session keeps working everywhere, including the scoped route.
 #[tokio::test]
 async fn a_full_session_still_satisfies_a_scoped_route() {

crates/cm-testkit/src/lib.rs

@@ -30,6 +30,10 @@ async fn server() -> &'static PgServer {
     SERVER
         .get_or_init(|| async {
             if let Ok(url) = std::env::var("CM_TEST_DATABASE_URL") {
+                // Only on the shared-server path. The testcontainer below is
+                // torn down with the process, so it has nothing to reap and a
+                // sweep there would be pure cost.
+                reap_stale_databases(&url).await;
                 return PgServer {
                     admin_url: url,
                     _container: None,
@@ -57,6 +61,86 @@ async fn server() -> &'static PgServer {
         .await
 }
 
+/// How long a test database may sit before another test process reaps it.
+///
+/// Comfortably longer than any test run, so a database in use by a
+/// concurrently-running binary is never a candidate. Nothing here needs to be
+/// prompt — the point is that the set stays bounded, not that it stays empty.
+const STALE_AFTER_MS: u64 = 2 * 60 * 60 * 1000;
+
+/// Drop test databases left behind by earlier runs.
+///
+/// `test_pool` creates a database per test and nothing ever dropped it. On the
+/// testcontainer path that is invisible: the container dies with the process
+/// and takes them with it. But `CM_TEST_DATABASE_URL` points at a SHARED
+/// server that outlives the run — which is the path CI uses and the path
+/// `.cargo/config.toml` sets for local development — so on both of those every
+/// database ever created is still there.
+///
+/// Measured before writing this: **3,546 databases, 38 GB** on one developer
+/// machine. It grows with every `cargo test`.
+///
+/// Age comes from the name, not the catalogue. Postgres records no creation
+/// time for a database, but the names are `test_<uuid-v7>` and UUIDv7 puts the
+/// millisecond timestamp in its first 48 bits — the same property
+/// `mission_runtime::container_name` relies on.
+///
+/// Best-effort throughout: a test must never fail because housekeeping could
+/// not run.
+async fn reap_stale_databases(admin_url: &str) {
+    let Ok(admin) = PgPoolOptions::new()
+        .max_connections(1)
+        .connect(admin_url)
+        .await
+    else {
+        return;
+    };
+    let names: Vec<String> = sqlx::query_scalar(
+        "SELECT datname FROM pg_database WHERE datname LIKE 'test\\_%'",
+    )
+    .fetch_all(&admin)
+    .await
+    .unwrap_or_default();
+
+    let now_ms = std::time::SystemTime::now()
+        .duration_since(std::time::UNIX_EPOCH)
+        .map(|d| d.as_millis() as u64)
+        .unwrap_or(0);
+    let mut dropped = 0usize;
+    for name in names {
+        let Some(created) = uuid_v7_millis(&name) else {
+            // Not a name we minted; leave it entirely alone.
+            continue;
+        };
+        if now_ms.saturating_sub(created) < STALE_AFTER_MS {
+            continue;
+        }
+        // FORCE terminates any leftover connection; without it a single stale
+        // session pins the database and the reap silently does nothing.
+        if sqlx::query(&format!("DROP DATABASE IF EXISTS {name} WITH (FORCE)"))
+            .execute(&admin)
+            .await
+            .is_ok()
+        {
+            dropped += 1;
+        }
+    }
+    if dropped > 0 {
+        eprintln!("cm-testkit: reaped {dropped} stale test database(s)");
+    }
+    admin.close().await;
+}
+
+/// The millisecond timestamp encoded in the leading 48 bits of a
+/// `test_<uuid-v7-simple>` name.
+fn uuid_v7_millis(db_name: &str) -> Option<u64> {
+    let hex = db_name.strip_prefix("test_")?;
+    if hex.len() != 32 || !hex.chars().all(|c| c.is_ascii_hexdigit()) {
+        return None;
+    }
+    u64::from_str_radix(&hex[..12], 16).ok()
+}
+
 /// Creates a unique database, runs all migrations, and returns a pool
 /// connected to it.
 pub async fn test_pool() -> PgPool {
@@ -93,3 +177,46 @@ fn swap_database(url: &str, db_name: &str) -> String {
         None => format!("{head}/{db_name}"),
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::{uuid_v7_millis, STALE_AFTER_MS};
+
+    /// Age comes from the NAME, because Postgres records no creation time for
+    /// a database. UUIDv7 puts the millisecond timestamp in its first 48 bits.
+    #[test]
+    fn a_test_database_name_carries_its_own_age() {
+        let id = uuid::Uuid::now_v7();
+        let name = format!("test_{}", id.simple());
+        let ms = uuid_v7_millis(&name).expect("a name we minted parses");
+        let now = std::time::SystemTime::now()
+            .duration_since(std::time::UNIX_EPOCH)
+            .unwrap()
+            .as_millis() as u64;
+        assert!(
+            now.saturating_sub(ms) < 5_000,
+            "a database created just now must read as new, or the reaper drops \
+             one another test process is still using"
+        );
+    }
+
+    /// Anything we did not mint is left alone.
+    #[test]
+    fn only_our_own_names_are_reapable() {
+        assert!(uuid_v7_millis("clawmates").is_none());
+        assert!(uuid_v7_millis("postgres").is_none());
+        assert!(uuid_v7_millis("template1").is_none());
+        // Right prefix, wrong shape — a human-made `test_scratch` survives.
+        assert!(uuid_v7_millis("test_scratch").is_none());
+        assert!(uuid_v7_millis("test_").is_none());
+        // Right length, not hex.
+        assert!(uuid_v7_millis(&format!("test_{}", "z".repeat(32))).is_none());
+    }
+
+    /// The window has to be longer than a test run, or the reaper deletes a
+    /// database out from under a binary running in parallel.
+    #[test]
+    fn the_stale_window_outlasts_any_test_run() {
+        assert!(STALE_AFTER_MS >= 60 * 60 * 1000);
+    }
+}

docs/NEXT-SESSION.md

@@ -7,12 +7,12 @@ than the agent's own account of it.
 
 ## State of the tree
 
-Local suite green: **107 test binaries, 796 tests** (`cargo test --workspace`), and the workspace builds with `--all-targets`.
-Five measurement missions ran on the local stack (`scripts/skill-use-run.sh`);
-all five are held 90 days and re-scorable with `--score <id>`.
-10 commits on `main` this pass, **not pushed** — a push to `main` auto-deploys
-to gw-04, and the container-tier work already deployed is unexercised there
-(see below).
+Local suite green: **108 test binaries, 815 tests** (`cargo test --workspace`).
+**Pushed** — 22 commits, CI green on gw-04, deployed.
+
+Eight measurement missions ran on the local stack
+(`scripts/skill-use-run.sh`); all are held 90 days and re-scorable with
+`--score <id>`.
 
 ## The premise of the last handoff's item 1 was wrong
 
@@ -132,44 +132,115 @@ which is the only reason they were found.
 `no_skill_shows_a_marker_the_parser_would_reject` guards the class, running the
 real parser over every marker in every skill's fenced blocks.
 
+### Trigger is measured, and the door is what made it possible
+
+`skill_use` scores Trigger from `ReadMcpResourceTool` calls, parsed through
+`mcp_skills::parse_uri` — the function that wrote the URI. Run 8, one mission,
+one clean A/B:
+
+| skill | delivered by | Trigger |
+|---|---|---|
+| `workspace-repo-commit-protocol` | retrieval | **pass** |
+| `web-search-triage` | inlined | not observable |
+| `structured-paper-summary` | inlined | not observable |
+| `scientific-writing-conventions` | inlined | not observable |
+
+Careful with what that proves: the retrieval was *instructed* by the task. It
+demonstrates the instrument, not a spontaneous relevance judgement.
+
+### Red-first is observable, and it needed neither ordering nor the diff
+
+The previous version of this list said the TDD check needed the repository
+diff. That was wrong, and `tdd-red-green-refactor` says why: *"Commit the
+RED-to-GREEN pair as one commit."* The failing test and its fix land together
+by instruction, so the diff and the commit history are as blind as tool
+ordering already was.
+
+The witness is what each run PRINTED, and the tap was discarding it. Claude
+Code's `PostToolUse` payload carries `tool_response` (stdout/stderr/
+interrupted) — verified against the binary. `bounded_response` keeps the END of
+that output, the opposite of `bounded_input`, because a command's meaning is
+its verdict and `cargo test` prints it last.
+
+    failing run then a passing one → Pass
+    every run failed              → Fail
+    every run passed              → NotObservable, because a test that never
+                                    failed is equally what a correct
+                                    implementation written first looks like
+
+## The four days after that pass went into infrastructure
+
+No product commits landed between 2026-08-21 and 2026-08-25. What did happen,
+re-verified live on the 25th:
+
+- `PasswordAuthentication no` is effective on gw-01/gw-02/gw-04 (checked with
+  `sudo sshd -T`, not by reading a config a drop-in can override), and
+  `fail2ban` is active on all three — **95 / 74 / 77 total bans**, so it is
+  catching real traffic. `ignoreip` must keep `100.64.0.0/10`: every operator
+  and every fleet node reaches these hosts from CGNAT space.
+- gw-02's three Postgres containers were published on `0.0.0.0` and are now
+  bound to `127.0.0.1` (5434 mindbridge, 5435 clawbridge, 5437 smartclaw).
+- Roughly 93G reclaimed; the largest single piece was a source-level leak of one
+  test database per test, fixed in `b58f034`.
+
+Two failure shapes worth keeping:
+
+- Recreating a DB container leaves the owning app holding **dead pool
+  connections**. The port binding reads perfect and the app still returns its
+  baseline status code, so a shallow check calls it done while every pool is
+  stale. Restart the owning unit and assert on the established-connection count.
+- A `grep` for the service name matched `smartclaw-email` before `smartclaw`,
+  so the wrong unit was restarted. Only the connection count being `0` caught it.
+
+**Open, and not safe to assume otherwise:** gw-02 has *no host firewall* —
+`INPUT` policy `ACCEPT`, `DOCKER-USER` empty. Ports 18789/3000/3010/8082 are
+bound `0.0.0.0` by native processes (a compose edit will not move them), and the
+only thing keeping them off the internet is an upstream cloud firewall the host
+cannot see. gw-05 and web-01 have no fail2ban and `sudo` there needs a password.
+
 ## Next, in order
 
-1. **The TDD check cannot confirm red-first, and that is structural.** Run 4
-   (`research_and_code`, real repo) edited `src/lib.rs` once — implementation
-   *and* `#[cfg(test)] mod tests` in the same write — then ran `cargo test`
-   five times. In Rust the unit test lives in the file under test, so that
-   ordering is what following the skill precisely looks like from outside. The
-   check detects "wrote source, never ran a test" and nothing more. If you want
-   red-first, it needs the diff (did the test exist before the impl?), not the
-   tool order.
+1. **Watch the first production mission.** Everything below the fold in this
+   document is now deployed and unexercised in prod, because prod has still
+   never run a mission. The door, the staffing, the attribution and the orphan
+   sweep all engage on the next launch. Prod auth is Clerk, so somebody has to
+   click.
 
-2. **Attribute tool calls to agents.** `record_vm_tools` writes
-   `agent_id: None`, because the container tap is per-container and all roles
-   share one. Every Skill-Use score is therefore per-**mission**, not per-role,
-   and the World's per-agent view gets nothing from the container tier. The
-   hook payload carries `session_id`; mapping it back to a turn is the fix.
+   ```
+   ssh gw-04 'docker logs clawmates_server_1 2>&1 | grep -E "skills door installed|drained .* tool call|orphans:"'
+   ```
 
-3. **Deploy the door** (`TOOL-CALL-ARCHITECTURE.md` §3). Config, not code:
-   `/zeroclaw-data/clawmates-mcp.json` plus a door-shaped provider alias. It is
-   now the single change that makes **Trigger** a real measurement, and the
-   precondition for skills moving from inlined bodies to progressive
-   disclosure — which would also cut the prompt cost in item 1.
+2. ~~**Measure Trigger properly.**~~ **Done — 2026-08-25.** `skill_delivery`
+   ships both arms; `index` sends name + `when_to_use` + a uri and the agent
+   fetches bodies through the door. Runs 9/10 in `SKILL-USE-BASELINE.md` are the
+   A/B: identical task, one server process, and **the first retrieval this
+   project has seen that the task did not ask for**. Each agent fetched the
+   skill bound to its own role and neither fetched another's. No Compliance
+   regression appeared — 34% fewer tokens, both arms judged met, deliverables
+   slightly larger. n=1 per arm, so that is a signal and not a rate.
 
-4. **Fold the microVM tier onto `container_tool_hooks`.** It has a gate and a
-   tap by a different route (`vm_tool_tap` installs into the guest,
-   `microvm_executor` drains inside the turn). Two mechanisms for one job is how
-   they drift — and the argument-discarding bug above lived in the shared parser
-   precisely because nobody looked at it from the container side. The fleet has
-   been offline for over a week, so this cannot be tested today.
+   What is left here is volume: run more pairs before believing any number, and
+   decide whether `index` becomes the default. It is currently opt-in per
+   mission (`config.skill_delivery`) or per deployment
+   (`CLAWMATES_SKILL_DELIVERY`).
 
-5. **Pull upstream's egress policy** — `0db7d999a feat(plugins): add shared
-   egress policy foundation (#9137)`. We are ~220 commits behind; this is the
-   one item worth taking, and it is defence for a problem we have not solved.
+3. **Fold the microVM tier onto `container_tool_hooks`.** Two mechanisms for
+   one job is how they drift — the argument-discarding bug lived in the shared
+   parser precisely because nobody looked at it from the container side. The
+   microVM path also still passes no turn agents, so its tool calls stay
+   unattributed. Blocked: the fleet has been offline for over a week.
+
+4. **Pull upstream's egress policy** — `0db7d999a feat(plugins): add shared
+   egress policy foundation (#9137)`. ~220 commits behind; this is the one item
+   worth taking, and it is defence for a problem we have not solved.
+
+5. **A narrow credential for the rest of the door.** `SCOPE_SKILLS_READ` covers
+   `/mcp/skills`. The `/mcp` door proper (`mcp_door.rs`) still authenticates
+   with a full session, and it is the one that can `delegate`. Nothing hands it
+   a token today; anything that does should not hand it a person's.
 
 ## Open decisions that are yours
 
-- **Push.** 10 commits are local. Pushing `main` triggers CI → auto-deploy to
-  gw-04.
 - **Self-authoring scope.** Agents apply their own `skill_candidate` items with
   no human click (`CLAWMATES_SKILL_SELF_AUTHORING=0` restores the gate).
   `identity_refinement` and `brain_consolidation` still wait for a human,

docs/SKILL-USE-BASELINE.md

@@ -286,6 +286,90 @@ skill itself names. It is recorded here rather than quietly corrected, because
 a measurement that hides its own false positives cannot be trusted about
 anyone else's.
 
+## Runs 9 and 10 — the delivery A/B, and the first unprompted Trigger
+
+Two `research_only` missions, **identical task text**, launched minutes apart
+against one server process. The task never mentions skills, MCP or retrieval —
+which is the whole point. Run 8 demonstrated the instrument, but its retrieval
+was *instructed by the task*; nothing there showed an agent judging relevance.
+
+| | run 9 (`inline`) | run 10 (`index`) |
+|---|---|---|
+| skills delivered | 4 | 4 |
+| prompt bytes (3 turns) | 8642 / 7689 / 10165 | 7329 / 5524 / 5762 |
+| tool calls recorded | 89 | **59** |
+| tokens (3 steps) | 52,191 | **35,090** |
+| `ReadMcpResourceTool` | 0 | **2** |
+| judge verdict | met | met |
+
+Per skill:
+
+| skill | run 9 trigger | run 10 trigger | boundary (both) |
+|---|---|---|---|
+| `web-search-triage` | not observable | **pass** | n/a |
+| `scientific-writing-conventions` | not observable | **pass** | n/a |
+| `structured-paper-summary` | not observable | n/a | n/a |
+| `workspace-repo-commit-protocol` | not observable | **FAIL** | pass |
+
+### What the retrievals actually show
+
+Attribution is the load-bearing detail, and it is only available because
+`attribute_sessions` maps a phase's tool calls back to the agent that made
+them:
+
+    Solveig (lead_researcher)  ->  skill:global/web-search-triage
+    Olamide (report_writer)    ->  skill:global/scientific-writing-conventions
+
+**Each agent reached for the skill bound to its own role, and neither reached
+for another role's.** That is a relevance judgement, not a sweep — an agent
+that fetched all four would have shown nothing except that it could.
+
+Two skills went unread. `structured-paper-summary` scores `NotApplicable`: its
+holder passed over it and nothing in that phase could check whether it should
+have, so calling that a miss would punish correct triage.
+`workspace-repo-commit-protocol` scores **Fail**, and that verdict is the one
+to argue with: the agent never fetched the procedure, yet every write it made
+landed inside the checkout, so `boundary` passes. It behaved correctly without
+reading the rule. Under the rule as written — an applicable skill offered and
+not read is a Trigger failure — that is a fail, and the pass beside it is the
+honest counterweight rather than a contradiction.
+
+### The regression the A/B existed to catch did not appear
+
+Progressive disclosure can only cost Compliance: under `inline` the procedure
+sits in front of the model whether or not it noticed it applied. It did not
+cost anything measurable here. The `index` arm used **34% fewer tokens and 30
+fewer tool calls**, both arms passed the independent judge, and the deliverables
+came out slightly larger, not thinner:
+
+    research/speculative-decoding.md   4870 -> 6182
+    research/evidence.md             10823 -> 11727
+    research/evidence-check.md        3340 -> 5336
+    research/questions.md             1894 -> 2402
+    research/REPORT.md                9867 -> 7901
+
+The `Edit` count is where the arms differ most (31 -> 5). That is a behavioural
+difference the measurement did not predict and cannot explain from one run
+each.
+
+### Two readings this data does not support
+
+**The prompt saving is small.** Skill bodies are a minority of a turn prompt,
+so withholding them cut 15-43% of the bytes, not the order of magnitude the
+framing suggests. Progressive disclosure is worth doing for Trigger, not for
+context economy.
+
+**Every `tool.call` in a phase carries the same `created_at`** — the drain
+timestamp, not the call time. All 59 rows in run 10 read `12:48:12`. Ordering
+tool calls by that column produces a confident, entirely fabricated narrative;
+the first draft of this section said the report writer had fetched both skills,
+because both retrievals appeared inside its turn window. Attribution by
+`agent_id` is the real answer and it says something different.
+
+**n = 1 per arm.** Two missions do not establish a rate. What they establish is
+that the axis now produces a signal at all, and that the control arm's
+structural blind spot is gone rather than papered over.
+
 ## Honest limits
 
 - **Five runs, one tier, two workflows.** Nothing here generalises to the

migrations/0082_mission_skill_delivery.sql

@@ -0,0 +1,16 @@
+-- Which arm of the skill-delivery A/B a mission ran.
+--
+-- 'inline'  — every pinned skill's body is appended to the turn prompt.
+-- 'index'   — the prompt carries name + when_to_use + uri; the agent fetches
+--             the bodies it judges relevant through the skills door.
+--
+-- Nullable, and NULL means 'inline'. Every mission that ran before this column
+-- existed ran inline, so a default would be a claim about history that a NULL
+-- correctly declines to make. `topology_exec::skill_delivery_mode` resolves
+-- NULL, an unrecognised value and a missing row identically, to the arm that
+-- requires nothing to be true.
+--
+-- Written once at launch by `mission_orchestrator`, which is the only place
+-- that knows whether the skills door installed — 'index' is refused without
+-- one, because an index the agent cannot fetch from is worse than no index.
+ALTER TABLE missions ADD COLUMN IF NOT EXISTS skill_delivery TEXT;

scripts/skill-use-run.sh

@@ -21,6 +21,13 @@
 #   REPO_ID       repository to check out; required by the coding recipes, and
 #                 the only way the TDD and commit checks can ever fire — a
 #                 repo-less run writes markdown and commits nothing
+#   DELIVERY      skill delivery arm   `inline` (default) or `index`
+#                 `index` sends name + when_to_use + a uri and makes the agent
+#                 fetch bodies through the skills door, which is the only arm
+#                 where Trigger is a question at all. Set per mission, so both
+#                 arms run against ONE server process — restarting between arms
+#                 would put a confound in the comparison that the numbers do
+#                 not show.
 #   TIMEOUT       seconds to wait      (default 1800)
 #   RETAIN_DAYS   hold events this long so the run stays re-scorable (default 90)
 
@@ -30,6 +37,7 @@ API="${API:-http://127.0.0.1:8080}"
 PG="${PG:-clawmates-postgres-1}"
 OWNER="${OWNER:-om[email protected]}"
 TEMPLATE="${TEMPLATE:-research_only}"
+DELIVERY="${DELIVERY:-}"
 TIMEOUT="${TIMEOUT:-1800}"
 RETAIN_DAYS="${RETAIN_DAYS:-90}"
 
@@ -67,7 +75,7 @@ api() { # api <token> <METHOD> <path> [json]
 jqv() { python3 -c "import sys,json;d=json.load(sys.stdin);print(d$1)"; }
 
 score() { # score <token> <mission-id>
-  local token="$1" id="$2"
+  local token="$1" id="$2" arm
   echo
   echo "── what the agents DID ─────────────────────────────────────"
   psql_ "select kind || '  ' || coalesce(target,'') ||
@@ -77,6 +85,11 @@ score() { # score <token> <mission-id>
           order by id;"
   echo
   echo "── Skill-Use ───────────────────────────────────────────────"
+  # Which arm ran, printed next to the scores it produced. A Trigger column of
+  # "not observable" means something different under each arm, and a report
+  # that does not say which one is not comparable to the next one.
+  arm=$(psql_ "select coalesce(skill_delivery, 'inline (unrecorded)') from missions where id='$id';" | tr -d '[:space:]')
+  echo "delivery arm: $arm"
   api "$token" GET "/api/missions/$id/skill-use" | python3 -m json.tool
 }
 
@@ -90,7 +103,7 @@ fi
 TITLE="${1:?title}"
 TASK="${2:?task description}"
 
-body=$(python3 - "$TITLE" "$TASK" "$TEMPLATE" "${REPO_ID:-}" <<'PY'
+body=$(python3 - "$TITLE" "$TASK" "$TEMPLATE" "${REPO_ID:-}" "$DELIVERY" <<'PY'
 import json, sys
 req = {
     "title": sys.argv[1],
@@ -99,6 +112,10 @@ req = {
 }
 if sys.argv[4]:
     req["repo_id"] = sys.argv[4]
+if sys.argv[5]:
+    # The recipe merges `phase_teams` INTO this object rather than replacing
+    # it, so an arm set here survives staffing.
+    req["config"] = {"skill_delivery": sys.argv[5]}
 print(json.dumps(req))
 PY
 )