All Claude Code modssayre4ux/autopilot
autopilot
Multi-agent orchestrator harness for Claude Code: command loop, ledger, dispatch protocol, review cycle, model-economics, and a registry-driven external-worker layer.
autopilot reaches L1 (reads) by its classified calls and passed claude plugin validate on Claude Code 2.1.302.
- Events hooked: 6
- API methods referenced: 15
- Access from classified calls: L1, reads: reads files, draws
- Unclassified calls: 2 (
$.state.get,$.state.set), full access unknown - Static scan, not a runtime test
Install hint
/plugin install autopilot --marketplace sayre4ux/autopilotFrom 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
L1 Reads filesother: $.state.get, other: $.state.set, reads files, drawsValidation
Passed on Claude Code 2.1.302View the source on GitHub Back to the list
What the scan recorded
- Observed events
- subagent spawns
- Hooks
session.start, command.run {command=ledger}, turn.complete, ui.render {component=Pane, requestId=autopilot-ledger}, agent.offer {agent=autopilot:security-engineer}, agent.spawn- API calls
$.agent.list, $.command.register, $.fs.exists, $.fs.read, $.session.model, $.session.root, $.session.surfaces, $.state.get, $.state.set, $.ui.close, $.ui.open, $.ui.panes, $.ui.resolve, $.ui.status, $.ui.toast- Validation on 2.1.302
- Passed
- Scanned revision
dff7a40dcebb- Marketplace passed
- autopilot-marketplace
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. 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/sayre4ux--autopilot--autopilot/)
[](https://mods.aidojo.si/mods/sayre4ux--autopilot--autopilot/)