Desk Runner — Project Management agent for Claude Code
Complete one briefed native Mac app task in the background through desk tools, then return a filtered read and checked cleanup.
How to install Desk Runner
Installs to ~/.claude/agents/aunysillyme-lean-computer-use-desk-runner.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/aunysillyme/lean-computer-use/HEAD/agents/desk-runner.md -o ~/.claude/agents/aunysillyme-lean-computer-use-desk-runner.md Restart Claude Code, or start a new session, for it to be picked up.
What Desk Runner does
name: desk-runner description: Complete one briefed native Mac app task in the background through desk tools, then return a filtered read and checked cleanup. Use when a fresh app context is needed, including when no cheap helper is available. tools: Read, Bash model: haiku effort: medium
You run the named Mac app task in a fresh context. Read the full brief before using a tool and keep every action inside its granted scope. Set `DESK=__DESK_DIR__`; the installer replaces this token wit
Alternatives in Project Management
- Flow Git — Use this agent for git operations — atomic commits, rebase, history cleanup, and style detection 523 ★
- Codex Artist — Image-generation subagent 249 ★
- Change Verifier — Use this agent after every change to the codebase to verify the project still lints, type-checks, tests, and b 204 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Mobile E2e Runner
Mobile E2E testing specialist for Android and iOS (native and Unity). Detects the project, picks Espresso/XCUI
Agy Runner
Drives one delegated task through the agy MCP server and reports back, so the orchestrator is not blocked whil
Queue Reviewer
Reviews the Jira service desk queue of exactly one client and reports what is new or changed since the previou
Implementation Worker
Implementation worker for one sbe work brief. Use when a plan task has already been briefed (sbe work brief) a
Buildhost Lead
Use PROACTIVELY and automatically — do not wait to be asked — as the Claude-Code node lead FOR an Apple-silico
Bonsai
Runs a task on the local Bonsai 2 27B model (PrismML ternary 27B, MLX, on this Mac) and returns its answer. Us
Related Skills
Synthetic Market Research
Agent skill for fast, cheap market research using LLM synthetic surveys + Semantic Similarity Rating (SSR). No
Clawdmeter Plus
A round AMOLED desk display for your live Claude Code usage, weather, background-agent health, and a daily voi
Tkflyc AI CLI
Run Claude Code, Codex, Antigravity and any OpenAI-compatible API as MCP tools with background jobs — registry