agentleFS
Sign inStart free
abersonaberson/skill-mesh/skills/build-observer/providers/claude.md

skill-mesh / providers

CLAUDE.md2 starsChanged 2 months agoMITView on GitHub

Claude provider entry point for build-observer; loads the canonical shared core.

We split this claude.md into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use Claude session JSONL, scratchpad identity, Artifact actions, or VS Code deep links only where available and requested by the core.

    line 15
  2. Very specific:

    Run the Step 5 uv run --project dev-observatory python .claude/skills/build-observer/scaffold_portfolio.py ...

    line 17
  3. Very specific:

    Never pass --public without --public-reason quoting the operator's own instruction.

    line 18
  4. Very specific:

    If a required Claude host tool is unavailable, use the core's documented fallback.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
claude.md

build-observer - Claude entry point

See ../core.md for the full specification.

Provider-specific instructions

  • Load the core in full before acting. Use Claude Code's Skill tool for named-skill calls and Agent/Workflow tools for isolated agents where the core requires those host abstractions.
  • Preserve the core's gates, retry limits, filesystem safety, and exact output contracts.
  • Use Claude session JSONL, scratchpad identity, Artifact actions, or VS Code deep links only where available and requested by the core.
  • Preserve the read-only contract exactly: never open registry.toml or snapshot.json for writing, never call registry.upsert_entry, and never run observatory scan/status (which would refresh the on-disk snapshot cache).
  • Run the Step 5 uv run --project dev-observatory python .claude/skills/build-observer/scaffold_portfolio.py ... validation call through the Bash tool, and relay its stderr KEPT/DROPPED/OMITTED lines close to verbatim -- that stderr IS the redline report, not a debug stream.
  • Never pass --public without --public-reason quoting the operator's own instruction. The script hard-refuses the pair; this wrapper never supplies a reason the prose invented.

Output normalization

Return only the core's operator-facing report: the TOML snippet, the verbatim redline lines, any [project.launch] follow-up, and the nothing-was-written reminder. Preserve exact locked strings and field names.

Unsupported capabilities

If a required Claude host tool is unavailable, use the core's documented fallback; otherwise halt visibly with required_tool_missing. Never weaken the read-only contract, and never emit a snippet the validator did not produce.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free