Menu
Debug router — choose between auto (agent-verified, narrow code fix) and manual (user-verified, deep spec context, in-place spec reconciliation)
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
Apply a Codex-only Belmont planning handoff packet after a plan-mode product-plan or tech-plan interview; write only the explicit .belmont files named in the packet without asking new planning questions.
Interactive planning session - create PRD and PROGRESS files for a feature
Technical planning session - create detailed implementation spec from PRD
Claude Code only. Drive a single feature to completion by self-pacing /belmont:implement → verify → next → status until no pending milestones remain.
Auto debug loop — investigate, fix, verify using agent-dispatched pipeline
Manual debug loop with deep Belmont context and in-place spec reconciliation — user-verified fix + correct the specs that let the bug exist
| name | debug |
| description | Debug router — choose between auto (agent-verified, narrow code fix) and manual (user-verified, deep spec context, in-place spec reconciliation) |
| alwaysApply | false |
This is the debug router. It directs you to the appropriate debug sub-workflow.
| Mode | Skill | Verification | Best for |
|---|---|---|---|
| Auto | /belmont:debug-auto | Verification agent checks each fix | Complex logic bugs, race conditions, issues needing automated testing, narrow code-only fixes |
| Manual | /belmont:debug-manual | User checks each fix (adds debug logs); deep Belmont context + in-place spec reconciliation after the fix | UI bugs, visual issues, known repro steps, bugs that exist because the spec drifted from reality, multi-feature debugging |
The two modes diverge sharply after the fix is confirmed:
Check the user's invocation text for mode hints:
Route to /belmont:debug-auto if the user mentions:
Route to /belmont:debug-manual if the user mentions:
If unclear, ask the user:
Which debug mode?
- Auto (
/belmont:debug-auto) — dispatches a verification agent to check each fix. Narrow code-only fix. More thorough but slower.- Manual (
/belmont:debug-manual) — you verify each fix yourself. Loads deep Belmont context (master PR_FAQ + master/feature PRD + TECH_PLAN + NOTES + latest MILESTONE.done). After the fix, walks the loaded specs and offers diffs to reconcile drift in place. Best for bugs that may have a spec-level root cause.
Once the mode is determined, invoke the corresponding skill. Do NOT continue in this file — hand off entirely to the sub-skill.
