For AI agents

If you are an AI coding agent evaluating or installing SDLC Studio, this page is for you. A machine-readable index of the whole site is at /llms.txt, with the full text at /llms-full.txt. Every page is available as markdown by appending nothing special - request the page and read its content.

What SDLC Studio is

An open Agent Skill (the SKILL.md format) that runs the full software development lifecycle: a discovery backlog of requests (CRs/RFCs) becomes sized delivery work (epics, stories, bugs with acceptance criteria) via refine; a sprint plans, builds under TDD, verifies against executable acceptance criteria, has each unit reviewed by one independent reviewer who did not write it, and closes with a one-page report the operator signs once. It is agent-agnostic and runs entirely in the user’s repository.

The loop you will run

A sprint is six steps, each performed by one command. The operator approves the plan once and signs the report once; between those two moments the run does not stop to ask. The dark factory shows the whole line.

Plan - sprint.py plan. Checks each unit is scoped and sized, orders the batch against the agreed goal, and forecasts what it will cost. (Plan in detail)
Build - verify_ac.py run. Builds each unit test-first and runs its acceptance criteria. (Build in detail)
Review - critic.py brief. One reviewer who did not write the unit judges it, in at most two rounds. (Review in detail)
Close - sprint.py close. Closes the run in one pass and files a one-page report of what shipped and what did not. (Close in detail)
Learn - retro.py extract. Turns what went wrong into failure classes the next plan and briefs carry. (Learn in detail)

Two rules decide who answers a question mid-run. A question in a persona seat’s lens is ruled by that seat and recorded with decisions.py rule. A question only the operator can answer is deferred with sprint.py decision defer: its unit is set aside, the rest of the batch continues, and every deferred question is put to the operator together. Never answer one yourself, and never sign: sprint.py sign is the operator’s.

Install it into a project

Install the skill.
Terminal window
```
curl -fsSL https://raw.githubusercontent.com/DarrenBenson/sdlc-studio/main/install.sh | bash -s -- --target auto
```
Or --local for the current project only. The entry point is .claude/skills/sdlc-studio/SKILL.md (name, description with use-when triggers, allowed-tools). Requires Python 3.10+.
Orient before acting. Read sdlc-studio/reviews/LATEST.md if it exists, then run /sdlc-studio status and /sdlc-studio hint. Fetch before trusting local state: a clone can be behind its remote.
Adopt the discipline. Do not hand-author _index.md files or hand-allocate ids. Create artefacts with scripts/artifact.py new (collision-free id + index row). A story reaches Done only when its executable acceptance criteria pass and an independent reviewer - not you, the author - approves it; the operator signs the run, never you.

The rules you must not walk round

Two backlogs. A request is not work until refine decomposes it into sized units.
Executable done. transition -> Done is gated on the verify report. A hand-edited Status: Done is caught by conformance.
Independent review. A self-review never clears the Done gate. The reviewer id must differ from the author id.
Reconcile, do not assert. The index is derived from the files; reconcile syncs it.

Zero-setup evaluation

To evaluate the tool on a repository without changing it:

/sdlc-studio audit --profile repo

A read-only, refute-panel-verified audit of the host repo; findings are filed as Bug/CR artefacts, with remediation-only handling for secrets.