agentleFS
Sign inStart free
L2-ootmL2-ootm/L2-ATLAS-PROJECT/AGENTS.md

L2-ATLAS-PROJECT

AGENTS.md2 starsChanged 5 months agoMITView on GitHub

Build L2 ATLAS as an AI operator/company cockpit using Hermes as the main runtime foundation and L2 and imported skill assets as reusable modules. Prototype in Python. Cement in Rust. Avoid C unless necessary. D-022 (accepted 2026-06-10) makes Rust-first immediate for all new infrastructure: Phase 7 gateway is Rust; new Python is confined to the Hermes-derived foundation surface, LLM adapters, and throwaway scripts. Update .planning/STATE.md after every meaningful step.

  • 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 31,700 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 repository2 other files it gives its agents.

The file

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

7 rules. About 1 is common, 4 are distinctive, and 2 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Common:

    Do not copy secrets or raw personal data into this repo.

    line 9
  2. Distinctive:

    Do not destructively reorganize existing repos.

    line 10
  3. Distinctive:

    Do not keep Hermes as a black-box dependency.

    line 11
  4. Distinctive:

    Keep actions auditable: reason, input, tool/action, output, verification.

    line 12
  5. Distinctive:

    Use flexible priority blocks, not rigid schedules.

    line 13
  6. Very specific:

    All Python code must follow migration prerequisites: frozen Pydantic v2 models, JSON-stable model_dump(), no circular deps, no heavy …

    line 33
  7. Very specific:

    Update .planning/STATE.md after every meaningful step.

    line 39

≈ “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

AGENTS.md — L2 ATLAS PROJECT

Mission

Build L2 ATLAS as an AI operator/company cockpit using Hermes as the main runtime foundation and L2 and imported skill assets as reusable modules.

Non-negotiables

  • Do not copy secrets or raw personal data into this repo.
  • Do not destructively reorganize existing repos.
  • Do not keep Hermes as a black-box dependency; ATLAS should be built from/enhance the Hermes foundation with documented changes.
  • Keep actions auditable: reason, input, tool/action, output, verification.
  • Use flexible priority blocks, not rigid schedules.

Architecture rule

Separate:

  1. raw sources;
  2. compiled wiki/memory;
  3. runtime execution;
  4. cockpit UI.

Language rule (D-013, cementation timing resolved by D-022)

Prototype in Python. Cement in Rust. Avoid C unless necessary. D-022 (accepted 2026-06-10) makes Rust-first immediate for all new infrastructure: Phase 7 gateway is Rust; new Python is confined to the Hermes-derived foundation surface, LLM adapters, and throwaway scripts.

  • Python is the current orchestration layer and is permanent for the Hermes plugin API.
  • The critical runtime (CLI, policy, executor, mission parser, state) will migrate to Rust module by module after behavior is validated in Python.
  • All Python code must follow migration prerequisites: frozen Pydantic v2 models, JSON-stable model_dump(), no circular deps, no heavy frameworks.
  • Approved Python deps: pydantic, prompt_toolkit, rich, pytest, ruff. No new frameworks without a new decision.
  • The native/ layer is Rust from the start (D-005).

Planning rule

Update .planning/STATE.md after every meaningful step.

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