vasilyu1983vasilyu1983/AI-Agents-public/AGENTS.md

AI-Agents-public

AGENTS.md94 starsChanged 32 days agoMITView on GitHub

Instructions for AI coding agents working in this repository.

Deletes or force-pushes

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 repository146 other files it gives its agents.
- agents/AGENTS.mdAGENTS.md
- hooks/AGENTS.mdAGENTS.md
- agents-hooksSkill
- agents-mcpSkill
- agents-memorySkill
- agents-skills-feedback-loopSkill
- agents-skillsSkill
- agents-subagentsSkill
- agents-swarm-orchestrationSkill
- ai-agentsSkill
- ai-architecture-advisorSkill
- ai-bot-builderSkill
- ai-coding-agents-observability-evalsSkill
- ai-coding-agents-pluginsSkill
- ai-coding-agents-provider-runtimeSkill
- ai-coding-agents-runtime-coreSkill
- ai-coding-agents-safety-envelopeSkill
- ai-coding-agents-settings-policySkill
- ai-coding-agentsSkill
- ai-coding-agents-stateSkill
- ai-coding-agents-surfacesSkill
- ai-context-layerSkill
- ai-data-curation-pretrainingSkill
- ai-deep-researchSkill
- ai-distributed-trainingSkill
- ai-evalsSkill
- ai-llm-inferenceSkill
- ai-llmSkill
- ai-local-model-opsSkill
- ai-ml-data-scienceSkill
- ai-mlopsSkill
- ai-ml-timeseriesSkill
- ai-post-trainingSkill
- ai-pretrainingSkill
- ai-product-operating-modelSkill
- ai-prompt-engineeringSkill
- ai-ragSkill
- ai-scaling-lawsSkill
- ai-vector-brainSkill
- ai-voice-botsSkill
- data-analytics-engineeringSkill
- data-lake-platformSkill
- data-metabaseSkill
- data-sql-optimizationSkill
- data-streamingSkill
- dev-ai-coding-metricsSkill
- dev-api-designSkill
- dev-context-code-graphSkill
- dev-context-engineeringSkill
- dev-context-multi-repoSkill
- dev-contribution-quality-analysisSkill
- dev-dependency-managementSkill
- dev-git-commit-messageSkill
- dev-git-workflowSkill
- dev-workflow-planningSkill
- docs-ai-prdSkill
- docs-codebaseSkill
- docs-notes-retrievalSkill
- document-docxSkill
- document-pdfSkill
- The first 60 shown.

The file

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

4 rules. About 1 is common, 3 are distinctive, and 0 are very specific to this project.

≈1
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
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

Distinctive:
Never hand-edit a generated file.
line 15
Distinctive:
Keep volatile facts (current versions, prices, limits) out of skill prose.
line 21
Distinctive:
Never invent a number or a citation.
line 22
Common:
Never commit secrets, credentials or personal data.
line 23

≈ “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

Repository Guidelines

Instructions for AI coding agents working in this repository.

Map

skills/universal/<name>/ — skills. SKILL.md holds the judgment; depth goes in references/, runnable code in scripts/, data a script reads in data/.
agents/claude/*.md — subagent definitions. agents/codex/*.toml is generated from them.
agents/teams/<id>/team.yaml — team recipes.
agents/workflows/<id>.manifest.json — workflow sources. <id>.js and <id>.codex-plan.json are generated.
hooks/, rules/ — opt-in hooks and language rules.

Rules

Never hand-edit a generated file. Edit the source, then regenerate:
- python3 skills/universal/agents-subagents/scripts/generate_workflows.py
- python3 skills/universal/agents-subagents/scripts/generate_codex_agents.py --write
- python3 skills/universal/agents-subagents/scripts/generate-team-diagrams.py
- python3 skills/universal/agents-subagents/scripts/generate_team_member_matrix.py
Validate an edited skill: python3 skills/universal/agents-skills/scripts/validate_skill.py skills/universal/<name>.
Keep volatile facts (current versions, prices, limits) out of skill prose. Give a lookup step instead.
Never invent a number or a citation. Quote only what you read in the source.
Never commit secrets, credentials or personal data.
In a shared working tree, do not run git stash, git reset --hard, path git checkout/git restore or git clean -f.

Checks

python3 skills/universal/agents-subagents/scripts/generate_workflows.py --check
python3 skills/universal/agents-subagents/scripts/generate_codex_agents.py --check
node agents/workflows/test-adversarial-review.mjs
python3 hooks/test_git_safety_guard.py
python3 hooks/test_config_guard.py

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