All Claude Code modsyasirshabbirservices/claude-mods
agents-panel
A pane listing the project agents in .claude/agents, with a run button for each
agents-panel reaches L2 (writes or runs) by its classified calls and passed claude plugin validate on Claude Code 2.1.302.
- Events hooked: 4
- API methods referenced: 17
- Access from classified calls: L2, writes or runs: drives Claude, writes the prompt box, reads files, draws
- Unclassified calls: 2 (
$.state.get,$.state.set), full access unknown - Static scan, not a runtime test
Install hint
/plugin install agents-panel --marketplace yasirshabbirservices/claude-modsFrom 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
L2 Writes or runsother: $.state.get, other: $.state.set, drives Claude, writes the prompt box, reads files, drawsValidation
Passed on Claude Code 2.1.302View the source on GitHub Back to the list
What the scan recorded
- Observed events
- Only what it hooks
- Hooks
session.start, command.run {command=agents-panel}, turn.complete, ui.render {component=Pane, requestId=agents-panel}- API calls
$.agent.list, $.agent.spawn, $.clock.every, $.clock.now, $.command.register, $.fs.exists, $.fs.list, $.fs.read, $.prompt.fill, $.state.get, $.state.set, $.ui.close, $.ui.invalidate, $.ui.open, $.ui.panes, $.ui.resolve, $.ui.toast- Validation on 2.1.302
- Passed
- Scanned revision
d3286593c471- Marketplace passed
- yasir-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. How the scan works.
More from yasirshabbirservices/claude-mods
- blast-radiusHolds rm -r, git reset --hard, git clean and git push --force, shows what they would change, and asks Proceed…
- context-barA bar above the prompt showing how the context window is used, by category
- decision-pickerWhen a reply asks you to approve decisions D1, D2, ..., shows toggles above the prompt; Approve drafts the re…
- fuelAbove the prompt only when you are near a limit: context window, plan limits with reset countdowns and an est…
- hover-revealDesktop app: masks API keys, tokens and passwords in replies and tool output; hover to show them
- local-syncCopies each file Claude changes under a source folder to the same path under a target folder (a local site's…
- model-routerClassifies each turn as mechanical, ordinary or hard and sets the model and reasoning effort to match, loggin…
- next-stepsUp to three suggested next prompts above the prompt box; a click or 1/2/3 drafts one, never sends
- plugin-confettiWhen an MCP tool call finishes, shows that plugin's real logo with a short confetti burst above the prompt; /…
- pulseA slim glowing bar above the prompt that shows what Claude is doing: breathing when idle, a wave while thinki…
- recorderRecords every tool call of a turn (name, short target, duration, error) and shows a timeline pane with /recor…
- token-weatherA live forecast of the context window, drawn above the prompt.
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/yasirshabbirservices--claude-mods--agents-panel/)
[](https://mods.aidojo.si/mods/yasirshabbirservices--claude-mods--agents-panel/)