Menu
Pipeline Step 4 — Completeness sweep to eliminate TODOs, mocks, stubs, and placeholder code before review.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Run a comprehensive code review across architecture, security, testing, naming, and patterns. Invokes relevant reviewer agents in sequence. Use before merging features or at the end of a phase. With --quorum, dispatches multi-model analysis for higher confidence.
Audit UI components for WCAG 2.2 compliance, semantic HTML, ARIA labels, keyboard navigation, color contrast, and responsive design.
Audit API endpoints for backward compatibility, versioning, OpenAPI compliance, pagination, rate limiting, and RFC 9457 error responses.
Review code for architecture violations: layer separation, sync-over-async, missing CancellationToken, improper DI. Use for PR reviews or code audits.
Fix a bug using TDD: reproduce with a failing test first, then implement the fix, then verify. Prevents regressions.
Review CI/CD pipelines for best practices: environment promotion, secrets management, rollback strategies, build caching, and deployment safety.
| name | planforge-step4-completeness-sweep |
| description | Pipeline Step 4 — Completeness sweep to eliminate TODOs, mocks, stubs, and placeholder code before review. |
| metadata | {"author":"plan-forge","source":".github/prompts/step4-completeness-sweep.prompt.md"} |
Pipeline: Step 4 of 5 (Session 2 — Execution)
When: After all slices pass (Step 3), before the Review Gate
Model suggestion: Any model / Copilot Auto (10% token savings) — pattern scanning works well on all models
Next Step:step5-review-gate.prompt.md(new session)
Replace <YOUR-HARDENED-PLAN> with your hardened plan filename.
Read these files first:
Now act as a COMPLETENESS SWEEP AGENT (see Section 6.1 of the runbook).
Scan ALL files created or modified during this phase for:
For each finding:
Output:
If ANY finding cannot be resolved without scope expansion: pause and report the blocker.
forge_sweep for structured TODO/FIXME/stub scanning with file locationsforge_diff with the plan file to confirm all changes are within scope before handoff to reviewUse MCP tools for structured results when available. Fall back to manual grep if MCP is not configured.
search_thoughts("common stubs", project: "TimeTracker", created_by: "copilot-vscode", type: "bug") — check if prior sweeps found recurring stub patterns so you can look for them proactivelycapture_thoughts([...findings], project: "TimeTracker", created_by: "copilot-vscode", source: "plan-forge-step-4-sweep", type: "convention") — batch capture patterns and conventions discovered during cleanup