All Claude Code modsNeedSomeFoodMr/claude-mods
agent-deck
A pane showing the main loop and every subagent of the session as pixel crabs, each under its role's hat: a short name, role, model, plan progress, context fill, tokens, estimated cost and time, with totals on top and the finished ones kept below; while agents work, one line above the prompt says how the run stands.
agent-deck reaches L2 (writes or runs) by its classified calls and passed claude plugin validate with warnings on Claude Code 2.1.302.
- Events hooked: 13
- API methods referenced: 16
- Access from classified calls: L2, writes or runs: drives Claude, writes the prompt box, draws
- Unclassified calls: 3 (
$.prompt.read,$.state.get,$.state.set), full access unknown - Static scan, not a runtime test
To install it, open the repository and follow the author’s setup instructions. Mods need Claude Code 2.1.287 or later.
Access
L2 Writes or runsother: $.prompt.read, other: $.state.get, other: $.state.set, drives Claude, writes the prompt box, drawsValidation
Passed with warnings on Claude Code 2.1.302View the source on GitHub Back to the list
What the scan recorded
- Observed events
- subagent spawns, every prompt, every tool call
- Hooks
session.start, command.run {command=agent-deck}, state.set {plugin=hud, key=signal}, session.measure, agent.offer, agent.spawn, prompt.submit, tool.describe {tool=mcp__agent-deck__plan}, tool.check {tool=mcp__agent-deck__plan}, tool.call, turn.step, turn.complete, ui.render {component=Pane, requestId=agent-deck}, ui.render {component=AbovePrompt}- API calls
$.agent.list, $.clock.every, $.clock.now, $.command.register, $.config.list, $.prompt.fill, $.prompt.read, $.session.model, $.session.usage, $.state.get, $.state.set, $.tool.register, $.ui.close, $.ui.open, $.ui.panes, $.ui.resolve- Validation on 2.1.302
- Passed with warnings
- Scanned revision
03d631f9d2e9
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.
More from NeedSomeFoodMr/claude-mods
- done-chimeA toast and a system sound when a long turn finishes, and a sound when Claude is waiting on a permission answ…
- filesA pane for finding and reading files without asking the model: an explorer with search by name that lights up…
- goalsA goals list above the prompt that Claude keeps current as it works: what is done, what it is on, and what co…
- hudOne row above the prompt: the context window as a coloured bar by what fills it, the rate-limit windows, the…
- quick-promptsA row of buttons above the prompt that drop a saved prompt into the prompt box. Hidden until /quick-prompts s…
- replayRecords the file edits of the last turn and steps through them as diffs in a pane.
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/NeedSomeFoodMr--claude-mods--agent-deck/)
[](https://mods.aidojo.si/mods/NeedSomeFoodMr--claude-mods--agent-deck/)