/debug
Investigate-then-decide root-cause analysis for a defect whose cause is unknown. No code changes — exits to {{CMD:fix}}, {{CMD:adr}}, or a no-action close.
$ npx -y skills add arbiterForge/codeArbiter --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/debug
Context preview
What this command does when you run it.
Investigate-then-decide root-cause analysis for a defect whose cause is unknown. No code changes — exits to {{CMD:fix}}, {{CMD:adr}}, or a no-action close.
Command definition
debug.mddescription: Investigate-then-decide root-cause analysis for a defect whose cause is unknown. No code changes — exits to {{CMD:fix}}, {{CMD:adr}}, or a no-action close.
argument-hint: "<observed symptom>"{{CMD:debug}} — root-cause investigation
Investigates a defect, anomaly, or unexpected behavior whose cause is not yet known. Separates investigation from implementation: no code is modified while debugging. Describe the symptom with enough fidelity that another operator could reproduce it — observed behavior, reproduction steps (or intermittent-trigger profile), and environment. Vague descriptions ("it's flaky") are rejected; the orchestrator asks for clarification before routing.
If the cause is already known and a regression test is already named, invoke `{{CMD:fix}}` directly.
Routes to
The `debug` skill (`{{PLUGIN_ROOT}}/skills/debug/SKILL.md`) — five gated phases: symptom capture, hypothesis generation, evidence gathering, root-cause decision, handoff. Phase 4 forces one named exit:
- **(a) Confirmed bug → `{{CMD:fix}}`**, carrying the confirmed bug statement, cited evidence, and a named
regression test obligation tied to the minimal repro.
- **(b) Behavior/design ambiguity → `{{CMD:adr}}`**, with the ambiguity statement and evidence ledger,
authored only with explicit user attribution.
- **(c) No-action close** — symptom and rationale appended to
`{{PROJECT_DIR}}/.codearbiter/open-tasks.md`.
A real finding that is out of scope for those exits is marked inline `[NEEDS-TRIAGE]` and the investigation continues.
When NOT to use
- Known bug with a named regression test → `{{CMD:fix}}` directly.
- Design discussion with no failing behavior → `{{CMD:adr}}`.
- New feature → `{{CMD:feature}}`.
- A general "why does it behave this way" question with no defect → `{{CMD:btw}}`.
- Re-entry from inside `{{CMD:fix}}` or `{{CMD:adr}}` → exit that command first (routing-cycle prevention).
Hard gate
MUST NOT modify any code during Phases 1–5 — code changes belong to `{{CMD:fix}}`. MUST exit Phase 4 with exactly one of (a)/(b)/(c). Exit (a) MUST carry a regression test obligation. Exit (b) MUST obtain user attribution before any `{{CMD:adr}}`. MUST NOT promote INCONCLUSIVE evidence to CONFIRMED without a cited source.
Read more
description: Investigate-then-decide root-cause analysis for a defect whose cause is unknown. No code changes — exits to {{CMD:fix}}, {{CMD:adr}}, or a no-action close.
argument-hint: "<observed symptom>"{{CMD:debug}} — root-cause investigation
Investigates a defect, anomaly, or unexpected behavior whose cause is not yet known. Separates investigation from implementation: no code is modified while debugging. Describe the symptom with enough fidelity that another operator could reproduce it — observed behavior, reproduction steps (or intermittent-trigger profile), and environment. Vague descriptions ("it's flaky") are rejected; the orchestrator asks for clarification before routing.
If the cause is already known and a regression test is already named, invoke `{{CMD:fix}}` directly.
Routes to
The `debug` skill (`{{PLUGIN_ROOT}}/skills/debug/SKILL.md`) — five gated phases: symptom capture, hypothesis generation, evidence gathering, root-cause decision, handoff. Phase 4 forces one named exit:
- **(a) Confirmed bug → `{{CMD:fix}}`**, carrying the confirmed bug statement, cited evidence, and a named
regression test obligation tied to the minimal repro.
- **(b) Behavior/design ambiguity → `{{CMD:adr}}`**, with the ambiguity statement and evidence ledger,
authored only with explicit user attribution.
- **(c) No-action close** — symptom and rationale appended to
`{{PROJECT_DIR}}/.codearbiter/open-tasks.md`.
A real finding that is out of scope for those exits is marked inline `[NEEDS-TRIAGE]` and the investigation continues.
When NOT to use
- Known bug with a named regression test → `{{CMD:fix}}` directly.
- Design discussion with no failing behavior → `{{CMD:adr}}`.
- New feature → `{{CMD:feature}}`.
- A general "why does it behave this way" question with no defect → `{{CMD:btw}}`.
- Re-entry from inside `{{CMD:fix}}` or `{{CMD:adr}}` → exit that command first (routing-cycle prevention).
Hard gate
MUST NOT modify any code during Phases 1–5 — code changes belong to `{{CMD:fix}}`. MUST exit Phase 4 with exactly one of (a)/(b)/(c). Exit (a) MUST carry a regression test obligation. Exit (b) MUST obtain user attribution before any `{{CMD:adr}}`. MUST NOT promote INCONCLUSIVE evidence to CONFIRMED without a cited source.
When you can't trust yourself with your code base, trust Arbiter.
Repo: arbiterForge/codeArbiter
Other commands on codearbiter.
- /add-dep
Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.
Open command - /adr-status
Report the health of Architecture Decision Records — aged, unchallenged, supersession candidates, unresolved CONFIRM-NN. Read-only.
Open command - /adr
Author a numbered, dated, user-attributed Architecture Decision Record under .codearbiter/decisions/.
Open command - /arbiter
Exit maintainer dev mode — restore orchestration, remove the dev marker, log the exit.
Open command - /audit
Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.
Open command - /btw
Lightweight Q&A about the project — answer from context and return, no routing, no state change.
Open command