agentleFS
curv-institutecurv-institute/atlas/AGENTS.md

atlas

AGENTS.md0 starsChanged 4 months agoMITView on GitHub

This is the canonical instruction file for any AI coding agent working in this repo (Codex, Claude Code, Gemini CLI, Cursor, opencode, Aider, ...). It's plain markdown - read it and follow it. CLAUDE.md, GEMINI.md, and .cursor/rules/ all redirect here so every agent gets the same rules. Atlas is a documented command surface for rigorous, agent-assisted research and development - a hub that maps and governs many concurrent repos/work areas, where a result or change only counts after it survives…

The file

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

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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. Very specific:

    Ownership gate: Before starting/redoing/prepping work that another thread/area may own, run the mediate procedure: in-bounds → proceed.

    line 42
  2. Distinctive:

    Verification hygiene: Run gated/verification commands from a clean shell with an explicit absolute cwd.

    line 47
  3. Distinctive:

    Record additively: Never delete history; supersede with a banner.

    line 50
  4. Distinctive:

    Conciseness: Don't flood context with raw tool output - pipe big output to a file and summarize.

    line 52
  5. Very specific:

    Style (no AI tells): Avoid em dashes, smart quotes, buzzwords, and filler constructions.

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 42,283 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 - Atlas (agent entry point)

This is the canonical instruction file for any AI coding agent working in this repo (Codex, Claude Code, Gemini CLI, Cursor, opencode, Aider, ...). It's plain markdown - read it and follow it. CLAUDE.md, GEMINI.md, and .cursor/rules/ all redirect here so every agent gets the same rules.

Atlas is a documented command surface for rigorous, agent-assisted research and development - a hub that maps and governs many concurrent repos/work areas, where a result or change only counts after it survives an attempt to break it.

Orient first (read these)

  1. OPERATING_GUIDE.md - the method: lifecycle, claim hygiene, confound catalog, pre-claim checklist.
  2. CURRENT_STATE.md - the single canonical state surface (live claims, withdrawn register, open work). If anything disagrees with this file, it wins.
  3. OWNERSHIP.md - who/what owns which area (consulted before you touch anything - see Workflows § mediate).
  4. REPOS.md - the repos this hub governs (register one with /add-repo <path>).
  5. Home.md - index of topics/experiments.

The loop (research or development)

Scope → cheap pilot → preregister (freeze the bar, with units, before the run) → build/run → gate (an evaluator emits the verdict to a file) → adversarial review (try to refute it) → record additively in CURRENT_STATE.md. For dev: spec → build → test/verify → review → record. Pre-state the bar; verify adversarially; record everything additively (withdrawals stay on the page).

Workflows (portable procedures)

Each is a self-contained procedure in .claude/skills/<name>/SKILL.md - plain markdown any agent can read and follow. Claude Code also exposes them as slash commands (/research etc.); other agents: when the user asks for one (or the situation matches), open the file and follow its steps.

WorkflowProcedure fileUse when
atlas-setup (alias onboard).claude/skills/atlas-setup/SKILL.mdfirst-time setup, or change project settings (name, ownership, agents, fleet, remote)
add-repo.claude/skills/add-repo/SKILL.mdregister a git checkout into this hub's REPOS.md (then syncs its knowledge)
sync-repo-knowledge.claude/skills/sync-repo-knowledge/SKILL.mdread a repo and write/refresh its wiki knowledge page
research.claude/skills/research/SKILL.mdwork a task end-to-end through the lifecycle
council.claude/skills/council/SKILL.mdadversarially verify a result / vet a plan / go-no-go
optimize.claude/skills/optimize/SKILL.mdmake a slow/expensive run faster without changing results
snapshot.claude/skills/snapshot/SKILL.mdplain-English status of the whole program
mediate.claude/skills/mediate/SKILL.mdbefore touching work another thread/area may own
registry-sync.claude/skills/registry-sync/SKILL.mdreconcile OWNERSHIP.md from live session logs (start/end of a research loop, or when stale)

Standing rules (all agents)

  • Ownership gate. Before starting/redoing/prepping work that another thread/area may own, run the mediate procedure: in-bounds → proceed; out-of-bounds → don't halt-and-wait and don't silently overstep - notify the owner with what/why/diff/risk and let them judge (human is fallback owner).
  • Claims vs candidates. A result is a candidate until it clears OPERATING_GUIDE.md §6. Say so. Name the measured quantity exactly; state N, units, CI. Pre-state thresholds with units.
  • Verification hygiene. Run gated/verification commands from a clean shell with an explicit absolute cwd; confirm the gate/output file is non-empty before reporting PASS. Re-derive load-bearing numbers from the raw artifact independently.
  • Record additively. Never delete history; supersede with a banner. Wrong results stay visible in the withdrawn register. Evidence/preregistration files are write-once (don't edit; correct via a new file).
  • Conciseness. Don't flood context with raw tool output - pipe big output to a file and summarize.
  • Style (no AI tells). Avoid em dashes, smart quotes, buzzwords, and filler constructions; see STYLE.md and run tools/style-check.sh before committing.
  • Git. Small commits; pull --rebase in shared clones; stage only what you changed; keep commit messages clear and specific.

Run the demo (any agent / human)

cd experiments/exp0_demo
uv run pilot/run.py --out raw.json                          # deterministic; raw results + content hash
uv run gate.py --raw raw.json --out gate_evaluation.json    # pre-stated thresholds → PASS/FAIL
cat RESULTS_demo.md                                         # verdict + a worked overclaim→walkback

Optional: multi-machine layer

fleet/ holds an optional inventory (fleet.yaml, copy from fleet.example.yaml) + discovery discipline for running across several machines. See fleet/AGENTS.md.

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.