harness-files/skills/rad-plan-audit/SKILL.md
Audit the two-doc planning set (Requirements + Master Plan) for codebase accuracy, cross-document cohesion, and explosion-readiness. Two modes: self-review (planner-time) and full audit (reporter subagent; orchestrator dispatches a planner subagent to apply fixes).
npx skillsauth add MetalHexx/RadOrchestration rad-plan-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Validates the planning set — {NAME}-REQUIREMENTS.md and
{NAME}-MASTER-PLAN.md — across three dimensions:
Phase Plans and Task Handoffs are deterministic explosion artifacts and
are out of scope here — they're validated post-execution by rad-code-review.
The audit rubric defines exactly what counts as a finding. The calibration clause governs severity.
| Mode | When to use | Workflow |
|------|-------------|----------|
| Self-Review | You are a planning agent creating or revising one of the two docs | self-review.md |
| Full Audit | You are the planner subagent dispatched to review both docs after creation | full-audit.md |
| Corrections | You are the planner subagent dispatched to apply an issues_found audit report | corrections-workflow.md |
Load the appropriate workflow document and follow it.
testing
Use this skill to understand, navigate, and organize the work-graph — the live map of projects in the system, what state each is in, how they relate to one another, and where their worktrees are. Use at brainstorm time when continuing a series or referencing existing work — orient on live state before exploring files.
development
Source control operations — commit code, open a PR, create a worktree, or clean up a worktree. All inputs for commit and PR come from the spawn prompt; worktree operations are interactive and driven from the main session.
data-ai
This skill can be invoked when the user starts talking about planning or executing a project. Use this skill to run a team of subagents through an automated SDLC process that helps them get work done safely and effectively.
testing
Continue a project through the orchestration pipeline. Ensures the Orchestrator runs as the primary agent — not as a subagent — so it retains full control of agent sequencing. Use for local, background, or cloud-based execution.