agentleFS
Sign inStart free
yogigodaraayogigodaraa/frame-map/CLAUDE.md

frame-map

CLAUDE.md0 starsChanged 26 days agoMITArchived repositoryView on GitHub

ProcViz: a five-agent LangGraph pipeline (FastAPI backend) that turns industrial SOP PDFs into animated spatial-temporal storyboards rendered with Konva. Walkthrough: docs/ARCHITECTURE.md. There are two stacks in this repo. Ask which one before editing: - v1 (deployed): root Vite app (src/) → backend/api/main.py → backend/agents/, backend/orchestrator/ - v2 (tested): frontend/ (CRA) → backend/procviz/

  • Installs packages

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    There are two stacks in this repo: Ask which one before editing:

    line 8
  2. Very specific:

    Every agent is run(state: PipelineState) -> PipelineState.

    line 28
  3. Distinctive:

    Every cloud call (Textract, Bedrock) must keep an offline stub path, so tests stay credential-free.

    line 29
  4. Very specific:

    Add new graph nodes in procviz/orchestrator.py::build_graph, and add a test in tests/test_pipeline.py.

    line 30
  5. Distinctive:

    Never commit real SOPs, customer documents or AWS credentials.

    line 34
  6. Distinctive:

    Don't remove stub mode or make tests depend on network access.

    line 35
  7. Very specific:

    Don't edit frontend/package-lock.json by hand (it's out of sync.

    line 36

≈ “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

CLAUDE.md

What this is

ProcViz: a five-agent LangGraph pipeline (FastAPI backend) that turns industrial SOP PDFs into animated spatial-temporal storyboards rendered with Konva. Walkthrough: docs/ARCHITECTURE.md.

There are two stacks in this repo. Ask which one before editing:

  • v1 (deployed): root Vite app (src/) → backend/api/main.py → backend/agents/, backend/orchestrator/
  • v2 (tested): frontend/ (CRA) → backend/procviz/

Commands

cd backend
pip install -r requirements.txt -r requirements-dev.txt   # Python 3.12
pytest                     # 56 tests, offline (stub mode, no AWS needed)
ruff check .               # rules in backend/ruff.toml
uvicorn procviz.main:app --reload --port 8000

# root Vite app (Node >= 22)
npm ci && npm run dev
npm run lint && npm run build

Conventions

  • Every agent is run(state: PipelineState) -> PipelineState; the schemas in procviz/schemas/ are the contract between agents.
  • Every cloud call (Textract, Bedrock) must keep an offline stub path, so tests stay credential-free.
  • Add new graph nodes in procviz/orchestrator.py::build_graph, and add a test in tests/test_pipeline.py.

Do not

  • Never commit real SOPs, customer documents or AWS credentials. Use synthetic sample procedures.
  • Don't remove stub mode or make tests depend on network access.
  • Don't edit frontend/package-lock.json by hand (it's out of sync; see issues).

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