docs: continuous_improvement reaches its subject; the brief, not the role prompt, aims it

v2 got the record delivered but never read it (0/50 calls; role prompts are
inert on missions and the reused v1 brief pointed at brains). v3, with a brief
aimed at PROJECT-MEMORY.md, read it, reported 4 MET / 0 UNMET and proposed
nothing, and was failed by the judge for summarising rather than quoting.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01WZb5A2kfVfjpdwSochkuHz

docs/TEMPLATE-MATURITY.md

@@ -65,7 +65,7 @@ holding (it was 55 of 85 dangling once).
 | `codebase_research` | code_archeologist architecture_mapper flow_tracer vault_scribe | research_readonly | 11 | **yes** — first run 2026-09-22 |
 | `papers_research` | domain_scout paper_reader library_curator | research_web_readonly | 8 | **yes** — first run 2026-09-22 |
 | `insight_research` | implementation_tracker novelty_hunter publication_drafter | research_readonly | 8 | no |
-| `continuous_improvement` | brain_inspector improvement_proposer improvement_evaluator | research_readonly | 7 | **runs, cannot reach its subject** |
+| `continuous_improvement` | brain_inspector improvement_proposer improvement_evaluator | research_readonly | 7 | **reaches its subject; right answer, judge-failed on quoting** |
 
 **Six of twelve are evidenced.** `backend` was exercised on 2026-09-22,
 the first time anything had been staffed from it: all five roles
@@ -122,6 +122,34 @@ template assumes long-lived agents that accumulate a record; the platform
 makes disposable ones. That is a design decision to resolve, not a bug to
 patch.
 
+**Retargeted (2026-09-22).** The decision taken: audit the *repo* brain,
+which is where missions actually write what they learn. The server now
+exports it as `/mission/memory/PROJECT-MEMORY.md`, one line per judged
+phase, and installs it into every mission that has a repository.
+
+Two runs followed, and they separate the channel from the steering:
+
+- **v2 (01a0cad8) — channel works, steering does not.** The 2.4 KB record
+  was installed. The agent made 50 tool calls, 0 of them touched it, 13
+  went to the roster, and the judge passed it. The brief and `done_when`
+  were reused from v1 ("read each agent's brain"), and the template's
+  retargeted role prompts are **inert on mission turns** (see
+  `prompt-injection-two-paths`). Rewriting `system_prompt` cannot aim a
+  mission; only the brief can, and nothing supplies one for this team.
+- **v3 (01a0cade) — right answer, failed by the judge.** With a brief and
+  `done_when` pointing at the record, 3 of 7 tool calls read it. The audit
+  states the record exactly (4 lines, MET 4 / UNMET 0), finds no pattern,
+  and files **zero** proposals ("a single UNMET line would be an incident;
+  this record has zero"), the correct result on an all-MET record. The
+  judge failed it, correctly by the letter: the condition required each
+  finding to *quote* the record lines, and the audit summarised them in a
+  table instead. `max_iterations` was 1, so there was no retry.
+
+So the subject is now reachable and the reasoning holds up. The unproven
+part is the case this team exists for, a record *with* failures. That
+needs a repository whose history contains UNMET verdicts, and a default
+brief so no caller has to write one. Still not counted as evidenced.
+
 **Two of the remaining six are still unevidenced**, and the other four
 are blocked on a target stack. The other nine are well-formed scaffolding:
 roles, prompts, brain seeds and resolving skills, and no run behind any of