agentleFS
Sign inStart free
Md-NisarMd-Nisar/neuron/AGENTS.md

neuron

AGENTS.md1 starsChanged 8 days agoApache-2.0View on GitHub

Run before delivery: Before changing LangChain or LangGraph versions, re-check official docs, update uv.lock, run all quality gates, and add regression tests for graph state and structured output behavior. Follow docs/AI_CODE_VERIFICATION.md. In short: keep changes small (under 400 lines where possible), write tests that fail without the change, never add a dependency without stating why and confirming it is the intended PyPI project, fill in the PR template's AI assistance, risk tier and verification sections, and keep the Co-Authored-By: commit…

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository4 other files it gives its agents.

The file

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

11 rules. About 0 are common, 4 are distinctive, and 7 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.

  • 7

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Keep HTTP concerns in api/.

    line 5
  2. Very specific:

    Keep request orchestration in services/.

    line 6
  3. Very specific:

    Keep graph construction and node routing in graphs/.

    line 7
  4. Very specific:

    Keep provider and LangChain harness construction in models/.

    line 8
  5. Very specific:

    Keep prompts under prompts/.

    line 9
  6. Distinctive:

    Do not add retrieval, queues, custom persistence, or subgraphs without a concrete requirement and ADR update.

    line 11
  7. Very specific:

    No raw eval or shell execution tools.

    line 27
  8. Distinctive:

    No live LLM calls in unit tests.

    line 29
  9. Distinctive:

    No mutating tools without authorization, idempotency, and tests.

    line 30
  10. Distinctive:

    No prompt-only security controls.

    line 31
  11. Very specific:

    Before changing LangChain or LangGraph versions, re-check official docs, update uv.lock, run all quality gates, and add regression tests …

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.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
AGENTS.md

Coding Agent Instructions

Architecture Rules

  • Keep HTTP concerns in api/.
  • Keep request orchestration in services/.
  • Keep graph construction and node routing in graphs/.
  • Keep provider and LangChain harness construction in models/.
  • Keep prompts under prompts/.
  • Do not scatter environment reads outside config/. There are two exceptions. observability/langsmith_governance.py overwrites LangSmith's own LANGSMITH_*/LANGCHAIN_* variables because the library reads them itself (ADR 0007, section 5). observability/telemetry.py sets OTEL_SEMCONV_STABILITY_OPT_IN for the same reason (ADR 0008, decision 3). tests/unit/test_entrypoint.py fails on any other os.environ/os.getenv use under src/.
  • Do not add retrieval, queues, custom persistence, or subgraphs without a concrete requirement and ADR update.

Commands

Run before delivery:

make format
make lint
make typecheck
make test
make security

Forbidden Patterns

  • No raw eval or shell execution tools.
  • No committed secrets.
  • No live LLM calls in unit tests.
  • No mutating tools without authorization, idempotency, and tests.
  • No prompt-only security controls.

Framework Upgrades

Before changing LangChain or LangGraph versions, re-check official docs, update uv.lock, run all quality gates, and add regression tests for graph state and structured output behavior.

Verifying AI-Generated Code

Follow docs/AI_CODE_VERIFICATION.md. In short: keep changes small (under 400 lines where possible), write tests that fail without the change, never add a dependency without stating why and confirming it is the intended PyPI project, fill in the PR template's AI assistance, risk tier and verification sections, and keep the Co-Authored-By: commit trailer. AI review comments are advisory; a human approves every merge.

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