zetetic-autopilot
by cdeust · ★ 0 · updated today
Automatic effort and model, and a quota that limits how many agents run, not how well one runs. Every request runs at the effort its grade calls for (zetetic-genius) and the main tool loop steps down the ladder. A subagent runs on the model its Agent call names, else the one its agent definition pins (read from the definition file, since agent.spawn carries only the call's), an inheriting type...
Install
/plugin marketplace add cdeust/claude-mods/plugin install zetetic-autopilot@claude-modsThen 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.startclassic.SessionStartsession.measureturn.stepagent.spawntool.callsession.appendturn.complete- API calls
$.agent.list$.clock.now$.env.get$.fs.exists$.fs.read$.fs.write$.session.cwd$.session.id$.session.model$.session.usage$.state.get$.state.set$.store.delete$.store.get$.store.keys$.store.set$.ui.toast- Can see
classic hookssubagent spawnsevery tool call- Reach
- level 2 of 3 other: $.state.getother: $.state.setwrites filesreads filesreads env varspersists statedraws
Origin
- How it got here
- Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
- Repository
- github.com/cdeust/claude-mods
- Path in repo
mods/zetetic-autopilot- Source commit
b31e910the exact code the scan read- Author
- @cdeust
- License
- No license declared — ask the author before reusing code.
- 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.
More from cdeust/claude-mods
cortex-cockpit
cdeust/claude-mods
The harness cockpit, a viewer: the phase every agent is in (PHASES panel, and main and the running agents in the band above the prompt), the advisor calls, what the insights learned (per-phase evidence, session outcomes from /insights, goals, the calibration and its proposals, with buttons to run /insights, apply, or open a calibration goal), Cortex memory health and grooming, the context...
cortex-guard
cdeust/claude-mods
Two rules no settings hook enforces, refused at the tool call: wiki pages and their generated ADR mirrors are written only through the Cortex wiki tool, and every git worktree lives at /.claude/worktrees/ / (one created there is registered with disk_hygiene.py).
cortex-wiki
cdeust/claude-mods
/wiki : compile a Cortex wiki page (Markdown with tikz blocks) to PDF through pandoc and xelatex, and open it.
harness-fleet
cdeust/claude-mods
The owner's interface to the plugin fleet: /fleet shows each owned plugin's installed and offered version, the repository's open PRs with their CI state and its open issues (defects first, feature requests set apart), and the session's harness signals. The mod only reads (gh pr list, gh issue list, git remote): every outward action starts with a button the owner presses (Review a PR, Take a...
mission-control
cdeust/claude-mods
A graphical pane of the harness at work: every agent of the turn as a swimlane coloured by phase, bar height its effort, with advisor calls and failed tool calls marked; the effort each phase is calibrated to; and each phase's learning curve from the insights ledger, with the calibration's moves. Drawn in pixels where the terminal has the kitty graphics protocol (kitty, Ghostty, outside tmux)...
zetetic-genius
cdeust/claude-mods
Grades every request before its turn starts (task class → effort rung, in one low-effort completion) and routes it to the genius reasoning patterns and problem-shaped skills whose trigger it matches, from the installed zetetic-team-subagents index; under enforce, the matched pattern's workflow rides beside the prompt. An analysis or critical request also carries one line asking for the advisor...
zetetic-insights
cdeust/claude-mods
The learning loop: every main turn is kept in a ledger across sessions (phase, effort, steps, failed tool calls, agents, advisor calls), joined with the outcomes observed at tool.call (commits kept or reverted, test exits, PR verdicts and merges, no transcript) and the ones /insights writes, and the project's goals; probe sessions are counted and kept out; a phase whose evidence says so gets...