All Claude Code modsaudichuang/jev-skill-suggestion
jev-skill-suggestion
Keeps the skill listing out of the context window and lets TypeSafe's Jev, a System One decision model, pick at most one skill per prompt from the skills' descriptions, the way TypeSafe's skill-suggestion cookbook does: one request ranks every skill and asks whether the prompt needs a skill at all, a second re-reads the top eight with their SKILL.md and can reject them all. The winner's SKILL.md is attached to the prompt, and /jev-skill-suggestion:setup lists every skill by name only, so the model can still load any of them, including one skill that names another. Falls back to the engine's built-in classifier when no key is set.
jev-skill-suggestion reaches L3 (network) and passed claude plugin validate with warnings.
- Events hooked: 5
- API methods referenced: 15
- Access from classified calls: L3, network: network, writes files, drives Claude, reads files, reads env vars, reads the transcript, draws
- Static scan, not a runtime test
Install hint
/plugin install jev-skill-suggestion --marketplace audichuang/jev-skill-suggestionFrom the repository's own marketplace. Confirm the plugin name in the repository's README before installing. Mods need Claude Code 2.1.287 or later.
Access
L3 Uses the networknetwork, writes files, drives Claude, reads files, reads env vars, reads the transcript, drawsValidation
Passed with warningsView the source on GitHub Back to the list
What the scan recorded
- Observed events
- every prompt, compaction, the jev-skill-suggestion:setup skill, every skill
- Hooks
prompt.attachment {type=skill_listing}, prompt.submit, session.end, session.compact, skill.prompt {skill=jev-skill-suggestion:setup}, skill.prompt- API calls
$.clock.now, $.clock.sleep, $.command.list, $.env.get, $.fs.exists, $.fs.list, $.fs.read, $.fs.write, $.http.fetch, $.model.classify, $.session.cwd, $.session.id, $.session.messages, $.ui.log, $.ui.status- Validation
- Passed with warnings
- Scanned revision
eb830bd43b26- Marketplace warnings
- jev-skill-suggestion
These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. What a mod can access and how the scan works.
Badge for your README
Authors can show the latest scan result in their README. Each badge links to this page.
[](https://mods.aidojo.si/mods/audichuang--jev-skill-suggestion--jev-skill-suggestion/)
[](https://mods.aidojo.si/mods/audichuang--jev-skill-suggestion--jev-skill-suggestion/)