srs-dd
CLAUDE.md0 starsChanged 32 days agoMITView on GitHub
AGENTS.md is the agent guide for this repository, and it is imported here so that every session starts with it in front of you rather than behind a pointer: It explains that this is the framework itself rather than a project using it, where the payload (skeleton/) ends and the framework begins, and the two rules that keep framework content out of other people's repositories. Claude-specific additions: - Invoke the srs skill before any code change that alters behavior —…
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- skeleton/AGENTS.mdAGENTS.md
- skeleton/CLAUDE.mdCLAUDE.md
- srs-arch-auditSkill
- srs-arch-harvestSkill
- srs-archSkill
- srs-auditSkill
- srs-baselineSkill
- srs-betSkill
- srs-buildSkill
- srs-checkSkill
- srs-commitSkill
- srs-harvestSkill
- srs-initSkill
- srs-newSkill
- srs-pageSkill
- srs-releaseSkill
- srs-reviewSkill
- srsSkill
- srs-upgradeSkill
The file
Files
SRS-DD framework repository
AGENTS.md is the agent guide for this repository, and it is imported here so that every session starts with it in front of you rather than behind a pointer:
@AGENTS.md
It explains that this is the framework itself rather than a project using it, where the payload (skeleton/) ends and the framework begins, and the two rules that keep framework content out of other people's repositories.
Claude-specific additions:
- Invoke the
srsskill before any code change that alters behavior — of a tool, a procedure, a guide, the payload or a CI template — when planning a task, and when the question is how this repository works rather than a change to it — it is itself an SRS-DD project. - To set SRS-DD up in another repository, use the
srs-initskill; it is available only here and is never copied into targets. - To author a new requirement through a dialog, use
srs-new; to audit spec ↔ code drift, test adequacy and the links between requirements, usesrs-audit. - To check a finished change, use the
srs-checkskill — it reads what each touched requirement asks for and offers to run exactly that; to read the specification as a page,srs-page. - To freeze the specification at a milestone, use
srs-baseline; to cut a release of the framework,srs-release. They are separate acts with separate numbers, and neither command commits or tags — that is left to the git client this repository is driven by.
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.

