system1
by ChengHung · ★ 0 · updated 28 days ago
0
用 System One 模型(目前 TypeSafe Jev)做判斷的 hook:派 sub-agent 前選 model;grilling 收尾拆題成 context/specs 規格檔(需 TYPESAFE_API_KEY,停用 plugin 即關閉)
Install
/plugin marketplace add cch-agent/claude-mods/plugin install system1@cchThen run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.
What it hooks into
From an automated scan with claude plugin validate, not a security review. Mods run with your permissions; read the code before installing.
- Events
session.startagent.spawntool.callprompt.submitskill.prompt- API calls
$.agent.register$.clock.now$.clock.sleep$.env.get$.fs.list$.fs.read$.fs.stat$.fs.write$.http.fetch$.process.run$.session.cwd$.tool.register$.ui.ask$.ui.status- Can see
subagent spawnsmcp__system1__submit_plan callsmcp__system1__confirm_plan calls? callsevery promptevery skillAgent calls- Reach
- level 3 of 3 networkruns processeswrites filesdrives Claudereads filesreads env varsdraws
Origin
- How it got here
- Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
- Repository
- github.com/cch-agent/claude-mods
- Path in repo
system1- Source commit
c7cb9c9the exact code the scan read- Author
- ChengHung @cch-agent
- License
- MIT
- First published
- Last pushed
- First listed here
Name and description come from the mod's own manifest. We link to the code; we don't host it, and it stays under its author's license.