state-machine-change
Skill31 starsChanged 2 months agoApache-2.0View on GitHub
Modify the Session or Grant state machine in packages/core with exhaustive transition tables and tests. Use whenever a state, event, guard, or effect changes.
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- db-migrationSkill
- ipc-commandSkill
- port-screenSkill
- provider-adapterSkill
- releaseSkill
- run-appSkill
- spec-lookupSkill
- ui-componentSkill
- visual-diffSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Update the State/Event unions and the transition table in packages/core/src/machines/<name>.ts (object-literal table, not if-chains) so …
- Very specific: line 14
Update the Mermaid diagram in docs/state-machines.md.
- Very specific: line 15
Run pnpm test -F @styx/core --coverage (100% on machines) and the state-machine-auditor subagent.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
State machine change: $ARGUMENTS
- Quote the spec §1 rule being implemented (
/spec-lookup 1). - Update the
State/Eventunions and the transition table inpackages/core/src/machines/<name>.ts(object-literal table, not if-chains) so exhaustiveness errors surface missing cells. Invalid pairs returnnull. - Effects are data (
{ type: 'startExpiryTimer', grantId, at }), executed by main. - Tests: table-driven over every (state, event) pair incl. invalid; invariants: needs-you never times out;
alwaysnever expires; one open grant ask per session. - Update the Mermaid diagram in
docs/state-machines.md. - Run
pnpm test -F @styx/core --coverage(100% on machines) and thestate-machine-auditorsubagent.
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.

