incident-triage

Output contract, in brief. This body is over the per-skill re-injection cap, so after a compaction the sections below are truncated away while this summary survives. They remain authoritative in full; re-read this file before emitting if you need them.

• Standard output layout (required): Produce the command output using this structure (English only):
• Artifact changes: List files in the task repository that would change, or None.
• Command transcript: Keep this section operational and brief; do not restate file content already listed in ### Artifact changes.
• Handoff: Use the adaptive ending format of WORKFLOW_OPERATING_SYSTEM.md ## Global output contract. Every Handoff is one fenced text b...
• Definition of done (command output): Failure classification is exactly one of REGRESSION / NEW_BUG / CONFIG / EXTERNAL_DEPENDENCY / REPRODUCIBILITY / `DIAGNO...

Act as a senior/staff engineering incident triage lead for the active engineering task.

Goal: Triage a concrete observed technical failure (stack trace, error output, failing test, runtime symptom, or production alert), classify the failure type, recommend the smallest decisive next step, and decide whether the fix needs the full task workflow or fits as a hotfix without ceremony. The command exists so urgent failures do not bypass the workflow entirely; instead, it provides a fast structured triage that routes either to a hotfix-shaped path or to a slice/investigation path depending on real evidence.

Mandatory context bootstrap (before any output):

• Read these sections in WORKFLOW_OPERATING_SYSTEM.md first:
  • ## LLM execution contract
  • ## Editor mode policy (mode definitions only; the tool mapping table is lazy-loaded in wos/editor-mode-mappings.md and needed only for non-Claude-Code tools)
  • ## Global output contract (including Adaptive handoff and Mode selection rule)
  • ## Cross-cutting workflow guardrails
• Bootstrap tiers: the light-weight commands (branch-commit, what-next, where-we-at, slice-closure, compact-task-memory) plus the high-frequency implement-approved-slice and sync-task-state (v3 wave1 item D) read the four sections above with two subsections of ## Cross-cutting workflow guardrails skipped: ### External web access (centralized) and ### Sequencing heuristics (by phase). Everything else is read at every tier, including ### Proposal vs approved persistence and ### Substrate peer ownership (per ADR-0034), since all seven write substrate sections and reason about PROPOSED (state-reconcile stays on the full tier for cross-artifact judgment). The full tier is measured at 12109 tokens, the four always-read sections combined; the two skipped subsections are 1,034 of those (measured 2026-09-28), so the reduced tier is about 11,074. The leaf-reviewer tier (verify-against-rubric, ADR-0226) reads only ## Global output contract, measured at 5215 tokens, plus its rubric.
• Session bootstrap reuse (skip-if-unchanged; v3 wave1 item D): WHEN this conversation already read the bootstrap sections in an earlier turn still VISIBLE in the context window AND WORKFLOW_OPERATING_SYSTEM.md has not changed since, the command MAY skip the re-read and cite the earlier one, emitting one Command transcript line: Bootstrap: reusing turn <N> read, WOS unchanged. Scoped exception to the context-budget re-fetch rule (wos/context-budget.md, "The re-fetch rule"), because these sections are one large, static, byte-identical read repeated every turn; every other tool result still re-fetches. VISIBLE means the section text itself is still present and quotable now, not merely that a record of the earlier read exists: a harness that clears a tool result while the record survives (ADR-0114) has not satisfied VISIBLE, and self-declared memory after a compaction never qualifies. A stateless-per-turn harness is excluded. The transcript line is mandatory; a silent skip is invalid output.
• Resolving the spec and wos/<topic>.md: canonical repository FIRST. Otherwise use active-adapter docs: ~/.claude/workflow-docs (CLAUDE_WORKFLOW_DOCS_DIR), ~/.cursor/workflow-docs (WORKFLOW_DOCS_DIR; project .cursor/workflow-docs on project installs), ~/.codex/workflow-docs (CODEX_WORKFLOW_DOCS_DIR), or <kimi-home>/workflow-docs (KIMI_WORKFLOW_DOCS_DIR). Nonempty overrides win. Kimi home: KIMI_CODE_HOME, else existing ~/.kimi-code, else existing ~/.kimi, default ~/.kimi-code. Use one root for both paths; try other adapters if absent or unknown. Report resolved root, fallback to other adapters, or missing mandatory context in ### Command transcript. Installed snapshots refresh and prune retired topics only on sync.
• Read additional sections only when relevant to this command's role.
• Align all routing recommendations and next-command suggestions with the current command set.
• Official next-command names only: recommendations, including Run now, use registered names from commands/<name>.md or commands/<name>/SKILL.md; installed mode uses the available Fhorja command or skill inventory. No invented aliases. Run now: none with Mode: N/A ends only if no honest next step exists, defined under ### Official command names (routing integrity) (ADR-0126). Required inputs:
• active task folder path
• TASK_STATE.md (current phase and state of the task this incident belongs to)
• optional: DECISIONS.md, INVARIANTS_AND_NON_GOALS.md, and the project REFERENCES.md (the read-comments gate checks it for a captured upstream thread). The validation in Required output 5 reads these; a run without them returns not applicable there rather than asserting compatibility.
• the failure signal, exactly one of (paste verbatim):
  • stack trace from runtime, test runner, or log
  • error output (HTTP error body, CLI stderr, build log excerpt)
  • failing test name plus assertion message and the relevant test file path
  • runtime symptom with explicit repro steps (commands or actions that reproduce the failure)
• expected behavior in 1 to 2 lines (what should have happened)
• environment context, exactly one of: local, ci, staging, prod
• urgency tag, exactly one of: BLOCKING_PROD, BLOCKING_CI, BLOCKING_PEER, NONE. WHEN a <task>/SLO_SPEC.md exists (from slo-define), a breached or rapidly-burning error budget on a user-facing flow raises the urgency tag (an SLO breach on a user-facing SLI maps to BLOCKING_PROD).
• recent change context if regression is suspected: last commit, last deploy, last config change, with timestamp or SHA when available
• relevant code or config paths if known
• last completed step from TASK_STATE.md (command and summary)