rpraharajrpraharaj/ai-sdlc/AGENTS.md

ai-sdlc

AGENTS.md0 starsChanged 15 days agoMITView on GitHub

This repository is the source of a portable AI SDLC pack.

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 31,843 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 repository66 other files it gives its agents.
- a11y-passSkill
- assess-changeSkill
- build-regression-packSkill
- charter-exploratorySkill
- classify-dataSkill
- commitSkill
- cut-releaseSkill
- data-changeSkill
- debugSkill
- design-experimentSkill
- diff-environmentsSkill
- draft-steercoSkill
- engineering-barSkill
- explain-codeSkill
- explore-codebaseSkill
- fix-ciSkill
- handoffSkill
- implement-changeSkill
- incident-triageSkill
- lean-reviewSkill
- map-dependenciesSkill
- map-design-handoffSkill
- map-processSkill
- open-prSkill
- performanceSkill
- plan-data-migrationSkill
- plan-incrementSkill
- plan-rollbackSkill
- plan-uatSkill
- prioritize-backlogSkill
- production-passSkill
- ready-to-mergeSkill
- record-decisionSkill
- refactor-safelySkill
- revert-changeSkill
- review-architectureSkill
- review-changeSkill
- review-pipelineSkill
- security-passSkill
- shape-workSkill
- ship-notesSkill
- spec-analyticsSkill
- spec-observabilitySkill
- start-projectSkill
- synthesize-discoverySkill
- triage-blockersSkill
- triage-defectSkill
- update-raidSkill
- verify-uiSkill
- write-api-examplesSkill
- write-architectureSkill
- write-designSkill
- write-dev-tasksSkill
- write-docsSkill
- write-integration-contractSkill
- write-nfrSkill
- write-opportunitySkill
- write-prdSkill
- write-requirementsSkill
- write-runbookSkill
- The first 60 shown.

The file

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

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

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

Very specific:
After edits, run python3 scripts/check-pack.py.
line 11
Very specific:
Do not add vendor-only frontmatter, vendor tool names, or orchestration DSLs to skills/, context/, templates/, agents/, playbooks/, or …
line 15
Distinctive:
Do not invent SLOs, users, or a live program’s systems of record in templates.
line 16
Common:
Do not commit secrets.
line 17
Very specific:
Do not put procedure steps in adapters/.
line 18

≈ “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

This repository is the source of a portable AI SDLC pack.

Do

Edit docs/ when the operating model changes. Keep one home per fact.
Edit skills/<name>/ using docs/reference/skill-standard.md. Frontmatter: spec fields only.
Edit agents/, playbooks/, workflows/ using the matching standard under docs/reference/.
Stay vendor-neutral. See docs/reference/portability.md.
After edits, run python3 scripts/check-pack.py.

Do not

Do not add vendor-only frontmatter, vendor tool names, or orchestration DSLs to skills/, context/, templates/, agents/, playbooks/, or workflows/.
Do not invent SLOs, users, or a live program’s systems of record in templates.
Do not commit secrets.
Do not put procedure steps in adapters/. Pointers only.

Commands

Install: n/a for this repo. Consuming repos follow INSTALL.md.
Run: n/a
Test: python3 scripts/check-pack.py
Lint / Typecheck / Build: none

Layout

context/ — templates for a consuming program’s always-on facts
skills/ — full standalone catalog (program + core engineering)
agents/ — nine permission profiles + optional personas
playbooks/ — one page per role
workflows/ — Markdown sequences with human gates
templates/consuming-AGENTS.md — starter AGENTS.md for a product repo
adapters/ — client pointers to AGENTS.md and .agents/skills/
evals/ — fixtures + static cases (scripts/check-evals.py)
docs/ — PRD, architecture, design, reference
scripts/check-pack.py — pack validator (includes static evals and validator/installer regression tests)
scripts/install-pack.py — non-overwriting initial installer; dry run unless --apply
docs/reference/pilot.md — consuming-program pilot evidence and exit criteria

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.

Reviews can't be read right now.

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