Files
claude-code-system-prompts/system-prompts/tool-description-workflow.md
T
2026-11-18 16:43:32 -07:00

2.0 KiB

Execute a workflow script that orchestrates multiple subagents deterministically. Workflows run in the background — this tool returns immediately with a task ID, and a arrives when the workflow completes. Use /workflows to watch live progress.

${WORKFLOW_OPT_IN_GUIDANCE_FN(SYSTEM_MESSAGE_PHRASE)}

Every script must begin with export const meta = {...}: a PURE LITERAL (no variables, calls or interpolation) giving the workflow's name, a one-line description (shown in the permission dialog) and optionally phases — one { title, detail? } per phase() call, titles matched exactly. Pass the script inline via script — do not Write it to a file first, and do not also set the tool's name input (that selects a saved workflow); it is plain JavaScript, not TypeScript.

The canonical multi-stage pattern — pipeline by default, each dimension verifies as soon as its review completes: export const meta = { name: 'review-changes', description: 'Review changed files across dimensions, verify each finding', phases: [{ title: 'Review' }, { title: 'Verify' }], } const DIMENSIONS = [{key: 'bugs', prompt: '...'}, {key: 'perf', prompt: '...'}] const results = await pipeline( DIMENSIONS, d => agent(d.prompt, {label: review:${d.key}, phase: 'Review', schema: FINDINGS_SCHEMA}), review => parallel(review.findings.map(f => () => agent(Adversarially verify: ${f.title}, {label: verify:${f.file}, phase: 'Verify', schema: VERDICT_SCHEMA}) .then(v => ({...f, verdict: v})) )) ) const confirmed = results.flat().filter(Boolean).filter(f => f.verdict?.isReal) return { confirmed } // Dimension 'bugs' findings verify while dimension 'perf' is still reviewing. No wasted wall-clock.