roronoazoroshao369roronoazoroshao369/vibe-coding-os/AGENTS.md

vibe-coding-os

AGENTS.md1 starsChanged 5 months agoMITView on GitHub

For detailed workflow guidance (workflow layers, skills, commands, templates, memory, verification, and merge readiness), see CLAUDE.md — the canonical Vibe Coding OS instruction file for AI coding agents. When using upstream inspiration: - Check references/index.json and read the relevant source doc and feature mapping first. - Update the source changelog when auditing upstream changes. - Never copy large upstream content or vendor code without license review and an explicit decision. - Keep attribution clean in ATTRIBUTIONS.md, NOTICE.md, and all registries.…

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 repository117 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- advanced-orchestrationSkill
- architect-agentSkill
- implementer-agentSkill
- quality-councilSkill
- reviewer-agentSkill
- tester-agentSkill
- writer-critic-pairSkill
- authoring-skillsSkill
- api-endpoint-qualitySkill
- async-job-qualitySkill
- auth-qualitySkill
- db-migration-qualitySkill
- frontend-state-qualitySkill
- acceptance-criteriaSkill
- adaptive-flowSkill
- adaptive-prompt-selectionSkill
- adversarial-code-reviewSkill
- architecture-decision-recordsSkill
- brainstormingSkill
- brownfield-spec-enhancementSkill
- bug-fix-lifecycleSkill
- checkpoint-validationSkill
- cicd-integrationSkill
- clarify-before-codeSkill
- claude-code-hooks-packSkill
- code-context-packSkill
- code-intelligence-reviewSkill
- context-policySkill
- context-rich-implementationSkill
- crash-proof-planningSkill
- critique-pass-protocolSkill
- dependency-aware-task-orderingSkill
- deprecation-migrationSkill
- disciplined-diagnosisSkill
- docs-authorSkill
- executing-plansSkill
- external-skillSkill
- finishing-a-development-branchSkill
- git-guardrailsSkill
- goal-driven-executionSkill
- grill-user-before-buildingSkill
- guard-bypass-protocolSkill
- improve-codebase-architectureSkill
- incremental-reviewSkill
- issue-slicingSkill
- lessons-learned-dbSkill
- loop-engineeringSkill
- model-aware-configSkill
- model-weakness-memorySkill
- multi-repo-learningSkill
- orchestration-workflowsSkill
- plan-driven-executionSkill
- plan-from-specSkill
- prd-from-contextSkill
- project-constitutionSkill
- prompt-architectureSkill
- prototype-before-commitmentSkill
- quality-engineSkill
- quality-execution-contractSkill
- The first 60 shown.

The file

Show its rules and text

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

16 rules. About 1 is common, 8 are distinctive, and 7 are very specific to this project.

≈1
Common · estimate
Many files like this have a rule of this kind.
≈8
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

Distinctive:
Prefer small, correct, reviewable changes over broad rewrites.
line 4
Distinctive:
Do not invent requirements.
line 5
Distinctive:
Keep plans concrete: files to touch, steps to take, and checks to run.
line 7
Very specific:
Run validation when possible, especially npm run validate for repository structure changes.
line 8
Distinctive:
Never claim success without verification.
line 9
Distinctive:
Keep external attribution clean.
line 10
Common:
Do not place secrets, private credentials, or unnecessary personal data in repository memory or examples.
line 11
Distinctive:
When using upstream inspiration:
line 17
Very specific:
Check references/index.json and read the relevant source doc and feature mapping first.
line 18
Distinctive:
Update the source changelog when auditing upstream changes.
line 19
Distinctive:
Never copy large upstream content or vendor code without license review and an explicit decision.
line 20
Very specific:
Keep attribution clean in ATTRIBUTIONS.md, NOTICE.md, and all registries.
line 21
Very specific:
Run npm run validate:references after changing reference files.
line 22
Very specific:
After adding/renaming/removing a command/skill/template, run npm run validate:traceability.
line 23
Very specific:
Use npm run references:clone for local upstream audit clones, but never stage or commit cloned source trees under references/upstreams/.
line 24
Very specific:
Before adopting any upstream, follow docs/UPSTREAM_ADOPTION_POLICY.md.
line 25

≈ “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

Agent Instructions for Vibe Coding OS

Inspect the repository before changing files. Understand existing structure, registries, and conventions.
Prefer small, correct, reviewable changes over broad rewrites.
Do not invent requirements. If the request is ambiguous, ask a clarifying question or record an explicit assumption.
For non-trivial coding, create or update a spec before implementation.
Keep plans concrete: files to touch, steps to take, and checks to run.
Run validation when possible, especially npm run validate for repository structure changes.
Never claim success without verification. If a check cannot run, state the limitation clearly.
Keep external attribution clean. Do not vendor third-party code, prompts, or docs unless license and attribution requirements are recorded.
Do not place secrets, private credentials, or unnecessary personal data in repository memory or examples.

Reference intelligence & attribution

For detailed workflow guidance (workflow layers, skills, commands, templates, memory, verification, and merge readiness), see CLAUDE.md — the canonical Vibe Coding OS instruction file for AI coding agents.

When using upstream inspiration:

Check references/index.json and read the relevant source doc and feature mapping first.
Update the source changelog when auditing upstream changes.
Never copy large upstream content or vendor code without license review and an explicit decision.
Keep attribution clean in ATTRIBUTIONS.md, NOTICE.md, and all registries.
Run npm run validate:references after changing reference files.
After adding/renaming/removing a command/skill/template, run npm run validate:traceability.
Use npm run references:clone for local upstream audit clones, but never stage or commit cloned source trees under references/upstreams/.
Before adopting any upstream, follow docs/UPSTREAM_ADOPTION_POLICY.md.
Respect the layer boundary in docs/workflows/core-vs-optional-runtime.md: Core is the identity; Runtime is opt-in and frozen-scope.

Codex-specific notes

Codex reads AGENTS.md as repository guidance. Use CLAUDE.md for tool-specific details not yet covered here.
For setup, see adapters/codex/README.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.

Check your setup, free