session-flow
CLAUDE.md3 starsChanged 5 months agoMITView on GitHub
Before starting unprompted work, consult the backlog at _devdocs/SEQUENCE.md. It is generated output: read it to find work, and never edit it. When asked to "implement the next task", run /session-next, which selects one open item, claims it, and records the outcome against its identity. Use /session-add-task to capture new work, /session-groom to fill in missing breakdowns, /session-gatekeeper to triage incoming issues, and /session-repair to survey and reconcile the work root when the sequence and the items disagree. _devdocs/todo/ is…
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- security-liability-auditSkill
- session-add-taskSkill
- session-brainstormSkill
- session-debugSkill
- session-delegationSkill
- session-gatekeeperSkill
- session-groomSkill
- session-initSkill
- session-nextSkill
- session-post-implementationSkill
- session-releaseSkill
- session-repairSkill
- session-research-designSkill
- session-task-planningSkill
- session-verifySkill
- update-architectureSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 4
Before starting unprompted work, consult the backlog at _devdocs/SEQUENCE.md.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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.
Files
<!-- session-flow:sequence -->Task Sequence
Before starting unprompted work, consult the backlog at _devdocs/SEQUENCE.md. It is generated
output: read it to find work, and never edit it. When asked to "implement the next task", run
/session-next, which selects one open item, claims it, and records the outcome against its
identity. Use /session-add-task to capture new work, /session-groom to fill in missing
breakdowns, /session-gatekeeper to triage incoming issues, and /session-repair to survey and
reconcile the work root when the sequence and the items disagree.
_devdocs/todo/ is the pre-import archive. Its files keep their names and stay where they are;
write nothing new there.
<!-- /session-flow:sequence -->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.