srnichols/plan-forge
Plan Forge guardrails for agentic delivery: plan, harden, execute, review and ship skills, the pipeline agents, and scheduled check templates. Pair it with the Plan Forge MCP server that setup installs in your project.
Run a recursive audit drain loop — discover findings from the running system, triage each into bug/spec/classifier lanes, repeat until convergence. USE FOR: end-to-end audit of a deployed or locally-running app, draining findings to zero. DO NOT USE FOR: single-shot tempering runs (use forge_tempering_run), one-off bug filing (use forge_bug_register), security-only scans (use /security-audit skill), code complexity review (use /forge-quench skill).
Guided end-to-end bug-fix workflow for Plan Forge tempering bugs — load → pre-fix review → write failing test → fix → validate → post-fix sweep → close. Composes /code-review, /clean-code-review, /forge-quench, and /test-sweep around the forge_bug_* tool surface so a fix never closes without a regression check.
Stack-agnostic Clean Code audit — module size, function-length/complexity (via your project's existing linter), long parameter lists, TODO/FIXME/HACK markers, commented-out code, debug-print leakage, and optional duplication detection. Produces a structured findings report with optional fix suggestions. Use before merges, at end of a feature, or as a regular hygiene pass.
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.
Guided plan execution — list available plans, estimate cost, choose mode, and execute with live progress. Use when you want to run a hardened plan through the orchestrator.
Systematically reduce code complexity while preserving exact behavior — measure, understand, propose, prove, report. Use after a feature is complete and tests pass, when code works but is harder to maintain than it should be.
Diagnose and resolve Plan Forge issues — failed runs, broken validation gates, misconfigured environments, stalled slices, and orchestrator errors. Use when a plan run fails or the forge behaves unexpectedly.
Run a full Plan Forge health diagnostic — environment, setup validation, and completeness scan. Use to verify your forge is properly configured and code is clean.
Comprehensive security audit — OWASP vulnerability scan, dependency audit, secrets detection, and combined severity report. Use before releases, after security incidents, or on a regular schedule.