All Claude Code modsservaes/cockpit
cockpit
Cockpit Board: one side panel with the account's usage windows, this chat's context and cache (warm or cold, the cold price, Keep warm, the Handoff note and Resume), live progress with a time estimate, goals with a Create goal box, agents, a Needs you section for everything that waits on you (held risky commands, hand-offs, the wrong-folder nudge), a CHANGES zone with the changed files, See code changes, See visual changes (the screen before and after) and Ship (six steps to live), and the file tree; the crew skill (/cockpit:crew, which runs a big task with a crew of worker agents), the goal meter, the agents and cache-tax ship inside it, all in one pane; above the prompt, two columns: the next steps ideas and Run It (Do it here, Hand to a cheaper agent, Open in a new chat, Split across agents, Plan first, then build, and the Codex 2nd opinion; the route the draft calls for is marked Suggested, with the lane and why), then what the message being typed will cost.
The scan could not record a complete footprint for cockpit, so its access is unknown; it passed claude plugin validate on Claude Code 2.1.303.
- Access: unknown, the footprint is incomplete
- Static scan, not a runtime test
Install hint
/plugin install cockpit --marketplace servaes/cockpitFrom 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
Unknown accessThe footprint is unavailable or incomplete.Validation
Passed on Claude Code 2.1.303View the source on GitHub Back to the list
What the scan recorded
- Footprint
- Unavailable or incomplete. Recorded events and calls below may omit access.
- Observed events
- Bash calls, every tool call, Read calls, TodoWrite calls, TaskCreate calls, TaskUpdate calls, mcp__cockpit__progress calls, mcp__cockpit__step calls, mcp__cockpit__ship calls, mcp__cockpit__handoff calls, mcp__cockpit__look calls, Agent calls, subagent spawns, every prompt, classic hooks, compaction
- Hooks
session.start, session.attach {surface=desktop}, tool.call {tool=Bash}, tool.call, tool.call {tool=Read}, tool.call {tool=TodoWrite}, tool.call {tool=TaskCreate}, tool.call {tool=TaskUpdate}, tool.call {tool=mcp__cockpit__progress}, tool.call {tool=mcp__cockpit__step}, tool.call {tool=mcp__cockpit__ship}, tool.call {tool=mcp__cockpit__handoff}, tool.call {tool=mcp__cockpit__look}, tool.call {tool=Agent}, turn.start, turn.step, turn.complete, agent.spawn, prompt.submit, classic.UserPromptSubmit, prompt.attachment, session.append {door=attachment}, classic.Stop, classic.SessionStart, classic.CwdChanged, classic.FileChanged, command.run {command=cockpit|board|filetree}, command.run {command=agents-info}, command.run {command=goal}, command.run {command=goals|goal-meter}, prompt.compose, command.run {command=ship}, session.compact, command.run {command=keepwarm}, command.run {command=cache-tax}, command.run {command=handoff}, command.run {command=replay}, ui.message- API calls
$.clock.after, $.clock.every, $.clock.now, $.command.list, $.command.register, $.command.run, $.env.get, $.fs.exists, $.fs.list, $.fs.read, $.fs.stat, $.fs.write, $.http.fetch, $.model.fork- Surface modules
hooks/rows.tsx- Validation on 2.1.303
- Passed
- Scanned revision
2caa45d6d58f- Marketplace passed
- my-mods
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/servaes--cockpit--cockpit/)
[](https://mods.aidojo.si/mods/servaes--cockpit--cockpit/)