Overview
/silver:bugfix is the Silver Bullet orchestrator for bugs, regressions, crashes, errors, and failing tests. It enforces triage-first discipline: classify the failure type before any investigation begins.
It never implements fixes directly — it orchestrates only. Investigation, planning, execution, review, and verification are all delegated to specialist skills.
The key design insight: three very different failure categories require three different starting points. Applying the wrong investigation technique wastes time and produces incomplete diagnoses. Triage first, investigate second.
/silver:bugfix uses the v0.48.3 APO catalog — catalog entity WF-SILVER-BUGFIX composes AF-ORIENT (optional) → AF-DEBUG → AF-PLAN → AF-EXECUTE → WF-POST-EXEC-GATES. See Composable Flows for the full catalog.
When to Use
Use /silver:bugfix for any of these entry trigger signals:
- "bug" / "broken" / "crash" / "error"
- "regression" / "failing test" / "not working"
- Any observation that something that used to work has stopped working
- A test that was green is now red
- An SB workflow or plan that failed mid-execution
silver:bugfix always takes precedence over silver:feature and silver:ui when triggered by a bug report.
Workflow Steps
Pre-flight
Silver Bullet reads silver-bullet.md §10 to load user workflow preferences before any step executes.
AF-DEBUG triage — classify failure type
Before any investigation, Silver Bullet presents a classification question:
The selection routes to one of three paths. All paths converge at Step 2 (TDD).
Path 1A — Known symptom, unknown fix
Invoked when triage selects A, OR after Path 1B/1C forensics completes and hands off here.
1A.1 — Systematic debugging hypothesis
Invoke /silver:debug in hypothesis mode. Purpose: structure the debugging hypothesis before executing investigation. Produces a testable hypothesis with reproduction steps.
1A.2 — Persistent debugging investigation
Continue in /silver:debug. Purpose: execute investigation with persistent state across context resets. After debugging completes, proceed to TDD regression.
Path 1B — Unknown cause, needs reconstruction
Invoked when triage selects B — session history is unclear or cause cannot be determined from current state.
1B.1 — Forensic cause reconstruction
Invoke /silver:forensics. Purpose: forensics skill that reconstructs cause from git history, artifacts, and state. Produces a cause classification report. After forensics completes: hand off to Path 1A with reconstructed context.
Path 1C — Failed SB workflow
Invoked when triage selects C — an SB plan, execution phase, or lifecycle command failed.
1C.1 — SB workflow post-mortem
Invoke /silver:forensics. Purpose: post-mortem for failed workflows (failed plans, broken state, incomplete phases). Produces a diagnosis of what went wrong in the workflow layer. After forensics completes: hand off to Path 1A with the diagnosis context.
AF-PLAN / AF-EXECUTE — TDD regression and fix
All three triage paths converge before fix implementation. Under AF-PLAN and AF-EXECUTE:
Invoke the SB tdd gate first — write a failing regression test (RED) before any fix code. Then /silver:plan (lightweight, 1–2 tasks) and /silver:execute --tdd. Verify the regression test is green after execution.
WF-POST-EXEC-GATES — Review, verify, secure, ship
After AF-EXECUTE, the standard post-execute tail runs:
Commands: /silver:review-request, /silver:review, /silver:review-triage, /silver:verify, /silver:secure, /silver:quality-gates, /silver:ship.
Non-Skippable Gates
/silver:quality-gatespre-ship (AF-QUALITY-GATE)/silver:verify(AF-VERIFY)/silver:secure(AF-SECURE)
Example Invocation
Silver Bullet presents triage options. You select A (known symptom, unknown fix). SB invokes /silver:debug to form and test a root-cause hypothesis. Root cause found → failing regression test → AF-PLAN / AF-EXECUTE → WF-POST-EXEC-GATES → ship.