copilot-finding-triage

Copilot Finding Triage

After a converge run's Copilot gate returns its findings, this skill tiers each one, verifies every code concern with an executed check, then acts on it. Findings scoped to style, type hints, or tests heal themselves inside the run. A logic, security, or behavior finding goes to a verifier that runs a check against HEAD: a confirmed defect joins the fix round carrying its repro, a refuted claim is answered on the thread with the check evidence, and only a finding the check leaves inconclusive pages the user and holds the run until they answer or a 45-minute deadline passes.

When this applies

Reach for this skill when a Copilot review on the round's HEAD returns findings inside one of these callers:

• autoconverge — the single-run converge workflow, at its Copilot wait-gate.
• pr-converge — the looping converge workflow, at each Copilot tick.

Each caller already fetches the review and carries a fix-and-push flow. This skill decides, per finding, whether that flow runs on its own or waits behind the user gate.

The tier split

Read the complete rubric in reference/tier-rubric.md. The short form:

• SELF-HEALING — the fix cannot change what a production caller sees at runtime. Style, type hints, misplaced or unused imports, magic-value extraction, reshapes limited to tests, doc-versus-code mismatches, and de-duplication.
• CODE CONCERN — the fix changes observable production behavior or needs a product decision. Logic or correctness defects, security, data handling, error-handling semantics, and concurrency.

A finding that straddles both tiers sorts to CODE CONCERN. Any doubt about the tier sorts the finding to CODE CONCERN.

The verification stage

Tiering names who might act; the verification stage between tiering and the user gate settles it for every code concern. Each code-concern finding goes to its own verifier agent, all in parallel, inside the run. The verifier runs a check against the flagged HEAD and returns one of three verdicts.