agent-sdlc
llms.txt2 starsChanged 4 months agoApache-2.0View on GitHub
A full-SDLC pipeline for AI coding agents — idea to a reviewed pull request — packaged as a plugin for Claude Code, Cursor, and OpenAI Codex, and as a directly-installable package for pi, with a zero-dependency enforcement checker (sdlc-check) and four standalone skills: three for documentation, plus repo-setup for a repo's operational baseline. The skills in skills/<name>/SKILL.md are the authoritative method; docs/ is the user- and contributor-facing guide; docs/specs/ is the repo's own pipeline output (it builds itself through the…
In this repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- acceptance-criteriaSkill
- architecture-designSkill
- buildSkill
- gateSkill
- getting-startedSkill
- handoffSkill
- ideaSkill
- lightSkill
- linear-syncSkill
- planSkill
- pr-reviewSkill
- repo-setupSkill
- techstackSkill
- writing-readmesSkill
- writing-repo-docsSkill
- writing-technical-docsSkill
The file
Files
# Agent SDLC > A full-SDLC pipeline for AI coding agents — idea to a reviewed pull request — packaged as a plugin for Claude Code, Cursor, and OpenAI Codex, and as a directly-installable package for pi, with a zero-dependency enforcement checker (sdlc-check) and four standalone skills: three for documentation, plus repo-setup for a repo's operational baseline. The skills in `skills/<name>/SKILL.md` are the authoritative method; `docs/` is the user- and contributor-facing guide; `docs/specs/` is the repo's own pipeline output (it builds itself through the pipeline it implements). ## Docs - [README](README.md): the front door — what it is, quickstart, install, layout. - [Quickstart](docs/quickstart.md): install + first run in two commands. - [Example run](docs/example-run.md): a five-minute worked example, idea to reviewed PR. - [Install](docs/install.md): Claude Code, Cursor, other agents, updates, requirements. - [The pipeline](docs/usage/pipeline.md): the stage chain, the traceability spine, the artifact model. - [Start anywhere](docs/usage/start-anywhere.md): enter at any stage, from any source. - [The light tier](docs/usage/light-tier.md): the compressed pass for small changes. - [sdlc-check](docs/usage/sdlc-check.md): the enforcement checker — invocation, rules, exit codes. - [Linear sync](docs/usage/linear-sync.md): the optional Linear mirror. - [Documentation skills](docs/usage/documentation-skills.md): writing-readmes / writing-repo-docs / writing-technical-docs. - [repo-setup](skills/repo-setup/SKILL.md): a repo's operational baseline — the AGENTS.md/AGENTS.local.md agent-instruction split, marked scaffolding skeletons, opt-in pipeline setup. - [Development](docs/development.md): clone, tests, skill authoring, releases. - [Architecture](docs/architecture.md): the repo's shape in one page. - [Contributing](CONTRIBUTING.md): branch/merge flow, commit convention, what review expects. ## Optional - [Project overview (living spec)](docs/specs/overview.md): the pipeline applied to this repo itself. - [Skill: getting-started](skills/getting-started/SKILL.md): the router + shared operating rules.
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
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.