osobh/clawmates
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: confirm the door from inside a mission, and correct a count I took from a transcript

Browse Source 
Run 8, all three agents, per-agent attributed:

  Pedro / Ebele / Ahmad — ListMcpResourcesTool, ReadMcpResourceTool

The agent's own report: 53 resources from `clawmates_skills`, and
`skill:global/workspace-repo-commit-protocol` read back as
`# Mission repo + commit protocol`. So the wiring works end to end, not
just the mechanism.

And a correction to the commit before this one. It recorded "58 MCP
resources" as a measurement. That number was the model's paraphrase in a
probe transcript, not an observation. `resources/list` returns 53 and
`select count(*) from skills` is 53.

Noted in the doc rather than quietly changed, because it is the same
error this project keeps making — a model's self-report treated as
evidence — and I made it in the very document arguing for measuring
things.

Co-Authored-By: Claude Opus 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_018i9Ten1LU4jUr5d7TAWda9
This commit is contained in:
Omar Sobh
2026-08-21 12:09:45 -07:00
co-authored by Claude Opus 5
parent 02d5f5a8c9
commit 42e014976d
1 changed files with 23 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/TOOL-CALL-ARCHITECTURE.md
+23 -2
View File
@@ -94,7 +94,7 @@ first:
``` ```
claude -p --mcp-config <doc> --strict-mcp-config "List the MCP resources you can see" claude -p --mcp-config <doc> --strict-mcp-config "List the MCP resources you can see"
→ 58 MCP resources. First two: skill:global/a11y-checklist, … → lists skill:global/a11y-checklist, … (see the count caveat below)
claude -p … "Read skill:global/workspace-repo-commit-protocol, reply with its first heading" claude -p … "Read skill:global/workspace-repo-commit-protocol, reply with its first heading"
→ # Mission repo + commit protocol → # Mission repo + commit protocol
@@ -127,10 +127,31 @@ narrow token and a route opts in by name; `/mcp/skills` is the only opt-in.
Measured live with one token: Measured live with one token:
``` ```
POST /mcp/skills → 58 skill resources POST /mcp/skills → 53 skill resources
GET /api/missions → 401 GET /api/missions → 401
``` ```
### And confirmed from inside a real mission
Run 8, all three agents, per-agent attributed:
```
Pedro ListMcpResourcesTool ReadMcpResourceTool Write …
Ebele ListMcpResourcesTool ReadMcpResourceTool Read …
Ahmad ListMcpResourcesTool ReadMcpResourceTool Write …
```
The agent's own report: *"53 MCP resources are available, all from the
`clawmates_skills` server … `skill:global/workspace-repo-commit-protocol` was
read and its first heading is `# Mission repo + commit protocol`."*
**Count caveat, and it is the usual lesson.** The first probe's transcript said
"58 MCP resources" and that number went into this document as though it were a
measurement. It was the model's own paraphrase. The authoritative count is 53 —
`resources/list` returns 53 and `SELECT count(*) FROM skills` is 53. A model's
self-report is not an observation, which this project has now learned three
separate times.
### What this does NOT yet buy ### What this does NOT yet buy
**Trigger is still not measured.** `pinned_skills_text` still inlines full skill **Trigger is still not measured.** `pinned_skills_text` still inlines full skill