# Aidlc Bugfix

> Run the AI-DLC workflow with the bugfix scope baked in — no scope detection. Fix a specific bug. Packaging over `/aidlc --scope bugfix`, which works without this skill.

- Skill: `aws-samples/aidlc-bugfix` (Agent Skill)
- Install (CLI): `npx skillmds@latest add aws-samples/aidlc-bugfix`
- Raw SKILL.md: https://api.skillmd.com/api/skills/aws-samples/aidlc-bugfix/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: aws-samples (https://skillmd.com/u/aws-samples)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/aws-samples/aidlc-bugfix

---


# AI-DLC — bugfix scope

Drive the AI-DLC engine with the **bugfix** scope fixed. This is the same
deterministic forwarding loop the `/aidlc` orchestrator runs, with `--scope
bugfix` baked into the first `next` so scope detection is skipped. The
engine owns all routing; the conductor persona arrives on the first directive's
`conductor_persona` field — adopt it for the whole run.

## The loop

1. `directive = bun .kiro/tools/aidlc-orchestrate.ts next --scope bugfix $ARGUMENTS`
2. Act on `directive.kind` exactly as the orchestrator does (run-stage / ask / print / error / done) — see `aidlc-common/protocols/stage-protocol.md`.
3. `bun .kiro/tools/aidlc-orchestrate.ts report --stage <directive.stage> --result <outcome> [--user-input "<text>"]` when the directive names a stage; omit `--stage` only for non-stage report round-trips.
4. Repeat from step 1 until `directive.kind == done`.

Pass `$ARGUMENTS` through verbatim after `--scope bugfix`; the engine parses
any flags (`--status`, `--stage`, `--test-run`, …) and the `--scope` from the
state file always wins on an existing workflow, so re-running a started workflow
resumes it. To run a different scope, use `/aidlc --scope <other>` instead.