All Claude Code modsianwilson97/claude-mods
cheap-worker
Spin up Claude Code workers from a picker: OpenRouter (any model) or Amazon Bedrock (Claude), as tmux panes or terminal tabs; team messaging between them
cheap-worker reaches L3 (network) and passed claude plugin validate on Claude Code 2.1.304.
- Events hooked: 5
- API methods referenced: 21
- Access from classified calls: L3, network: network, runs processes, writes files, drives Claude, reads files, reads env vars, reads mod state, persists state, draws
- Reads mod state: the scan does not record whose state, so this does not show that it reads another mod’s values
- Static scan, not a runtime test
Install hint
/plugin install cheap-worker --marketplace ianwilson97/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
L3 Uses the networknetwork, runs processes, writes files, drives Claude, reads files, reads env vars, reads mod state, persists state, drawsValidation
Passed on Claude Code 2.1.304View the source on GitHub Back to the list
What the scan recorded
- Observed events
- mcp__cheap-worker__workers calls
- Hooks
session.start, tool.call {tool=mcp__cheap-worker__workers}, command.run {command=worker}, session.receive, command.run {command=workers}, ui.render {component=PromptHint}, ui.render {component=Pane, requestId=cheap-worker}, ui.render {component=Pane, requestId=cheap-workers}- API calls
$.clock.after, $.clock.every, $.clock.now, $.command.register, $.env.get, $.fs.read, $.fs.write, $.http.fetch, $.process.run, $.session.cwd, $.session.send, $.state.get, $.state.set, $.store.get, $.store.set, $.tool.call, $.tool.register, $.ui.open, $.ui.resolve, $.ui.status, $.ui.toast- Validation on 2.1.304
- Passed
- Scanned revision
e0954c070e2d- Marketplace passed
- ianwilson-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.
More from ianwilson97/claude-mods
- agent-mapLive project file tree showing which file each agent (main, subagents, cheap workers) is editing (red 🔨) and…
- agent-progressAnimated per-agent progress bars (main agent, subagents, cheap-worker workers) driven by their task lists
- context-barLive context-window bar above the prompt: fill, compaction point and what fills it
- cw-paneLive pane of driver-seat cheap workers: running tasks, cost, fail and escalation rates from workers.tsv
- driver-seat-guardLearn mode: one-step pacing, no unasked web search, no work on todos you haven't reached
- evidence-bandOn status/audit prompts: require doc + file:line citations and show which sources Claude actually read
- quick-settingsA button under the prompt that opens a pane to switch /model and /effort; add a setting by adding one control
- skinsColour skins for all of Claude Code (Noir, Tokyo Night, Dracula, Catppuccin, Gruvbox, Everforest, Nordic, Mon…
- usage-meterFive-hour and weekly plan usage as one line under the prompt, with reset countdown and pace forecast
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/ianwilson97--claude-mods--cheap-worker/)
[](https://mods.aidojo.si/mods/ianwilson97--claude-mods--cheap-worker/)