Menu
Audit the codebase against the constitution — deterministic scan + your interpretation.
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
Domain Engineering diagnostic — shows what the classifier decides for an objective (CMIS/DAS/profile/skills/mode). Observation-only; never mutates or blocks.
Business-driven methodology entry point — classify (intake), create/advance an Operation or Business work context, and drive the intake → operation → nested-workflow flow. Host-neutral; dry-run by default.
Workflow Navigator — shows the current phase, deliverables, and next commands for an ADR-0057 workflow. Read-only; never mutates state.
Start a focused session on one objective — locks scope, blocks opportunistic refactors.
Deterministic QA gate (ADR-0055) — run the project suite; green + complete acceptance criteria ⇒ qa-approve testing cards into conclusion; red ⇒ report (and qa-reject only attributable failures).
L6 — autonomous feature pipeline. Drives the full squad: design → implement → review → test → log. Checkpoints can be manual or automatic.
| name | source-command-audit-tech-debt-sweep |
| description | Audit the codebase against the constitution — deterministic scan + your interpretation. |
Use this skill when the user asks to run the migrated source command tech-debt-sweep.
Run the deterministic scanner first, then interpret. Profile: $ARGUMENTS
(default full; quick = red zone only).
Run the scanner and write the board:
node contextkit/tools/scripts/tech-debt-scan.mjs --write # full
node contextkit/tools/scripts/tech-debt-scan.mjs --write --quick # red zone only
It checks: file length vs l5.lineBudget, SRP "And/Or/E" names, TODO/FIXME
markers, and React state-loops — and writes contextkit/memory/tech-debt-board.md.
Interpret the board with judgment the regex can't: which findings are real
debt vs acceptable cohesion? Which oversized file genuinely hides multiple
responsibilities? Add any smells the scanner can't see (leaky abstractions,
duplicated logic, missing error handling) — referencing AGENTS.md.
Feed the DevPipeline backlog — every finding becomes a tracked task:
node contextkit/tools/scripts/pipeline.mjs ingest contextkit/memory/tech-debt-findings.json --type chore
One backlog task per finding, auto-prioritized from severity (RED→P1, yellow→P2, low→P3), idempotent (re-running never duplicates).
Report + hand off. Surface the top 5 with the one-line fix each — the
board contextkit/memory/tech-debt-board.md is the full report. Do NOT fix here.
Tell the user the items are in the backlog and the priorities are
always editable: node contextkit/tools/scripts/pipeline.mjs prioritize <id> <P0-P3>
or /pipeline. Offer to open a focused /dev-start on the worst one.