agentleFS
Sign inStart free
bohewubohewu/agents_pipeline/CLAUDE.md

agents_pipeline

CLAUDE.md1 starsChanged 4 months agoMITView on GitHub

This is a Codex-first multi-agent workflow repository with a runtime-neutral source core. Claude Code support is a Tier 2 best-effort export. Generated .claude/agents/*.md files are outputs, not source. Canonical agent frontmatter contains only name, description, and kind. Schema validation:

The file

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. Very specific:

    Do not add OpenCode runtime surfaces.

    line 40
  2. Very specific:

    Do not reintroduce /run-goal or a goal orchestrator.

    line 41
  3. Distinctive:

    Do not add workflow-wide effort controls.

    line 42
  4. Very specific:

    Keep modes.json, orchestrator agents, status constants, schemas, and AGENTS.md synchronized.

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 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

Multi-Agent Pipeline Repository Guide

This is a Codex-first multi-agent workflow repository with a runtime-neutral source core. Claude Code support is a Tier 2 best-effort export.

Architecture

  • agents/*.md: canonical primary/subagent definitions.
  • modes.json: supported mode aliases and orchestrator routing.
  • protocols/: workflow contracts, JSON schemas, and fixtures.
  • skills/: portable repo-managed skills.
  • tools/status-event.js + tools/status-runtime/: status/checkpoint writer.
  • tools/agent-profiles/: neutral model tiers.
  • runtimes/claude/model-sets/: Claude model aliases.
  • scripts/export-claude-agents.py: Claude Code projection.

Generated .claude/agents/*.md files are outputs, not source. Canonical agent frontmatter contains only name, description, and kind.

Common commands

python3 scripts/export-claude-agents.py --source-agents agents --target-dir /tmp/agents-pipeline-claude --strict --dry-run
bash scripts/install-claude.sh --dry-run
python3 -m unittest discover -s tests -p 'test_*.py'
python3 scripts/validate-orchestrator-contracts.py
python3 scripts/validate-skill-frontmatter.py
node --test tests/status-runtime.test.js

Schema validation:

python3 tools/validate-schema.py \
  --schema protocols/schemas/<schema>.json \
  --input <payload>.json \
  --require-jsonschema

Invariants

  • Do not add OpenCode runtime surfaces; its last supported release is v0.26.1.
  • Do not reintroduce /run-goal or a goal orchestrator. Long-running work belongs to the host runtime's native task/session mechanisms.
  • Do not add workflow-wide effort controls. Verification, review, and repair are risk-derived; model reasoning belongs to the runtime.
  • Keep modes.json, orchestrator agents, status constants, schemas, and AGENTS.md synchronized.
  • Preserve resource teardown and evidence requirements for browser/server/process work.
  • Claude and Copilot adapters may document capability degradation instead of forking the canonical workflow.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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