From 555128b3e71050471a5acccc9fc7137b9ed260b0 Mon Sep 17 00:00:00 2001 From: pbean Date: Wed, 10 Jun 2026 09:07:32 -0700 Subject: [PATCH] fix(skills): pass diff output inline to the blind-hunter reviewer The Blind Hunter subagent intentionally has no tool access, but the review steps never said how {diff_output} should be delivered. Orchestrators typically wrote the diff to a temp file and asked the agent to read it, which silently fails (0 tool calls), and the 10-finding requirement then pushes the agent to hallucinate findings against code it never saw. State explicitly that the diff is passed inline in the subagent prompt, in both bmad-code-review step 2 and bmad-quick-dev step 4. Co-Authored-By: Claude Fable 5 --- .../4-implementation/bmad-code-review/steps/step-02-review.md | 2 +- .../4-implementation/bmad-quick-dev/step-04-review.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/src/bmm-skills/4-implementation/bmad-code-review/steps/step-02-review.md b/src/bmm-skills/4-implementation/bmad-code-review/steps/step-02-review.md index bbc1f9a82..3767af857 100644 --- a/src/bmm-skills/4-implementation/bmad-code-review/steps/step-02-review.md +++ b/src/bmm-skills/4-implementation/bmad-code-review/steps/step-02-review.md @@ -18,7 +18,7 @@ failed_layers: '' # set at runtime: comma-separated list of layers that failed o 2. Launch parallel subagents without conversation context. If subagents are not available, generate prompt files in `{implementation_artifacts}` — one per reviewer role below — and HALT. Ask the user to run each in a separate session (ideally a different LLM) and paste back the findings. When findings are pasted, resume from this point and proceed to step 3. - - **Blind Hunter** — receives `{diff_output}` only. No spec, no context docs, no project access. Invoke via the `bmad-review-adversarial-general` skill. + - **Blind Hunter** — receives inline `{diff_output}` only. No spec, no context docs, no project access. Invoke via the `bmad-review-adversarial-general` skill. - **Edge Case Hunter** — receives `{diff_output}` and read access to the project. Invoke via the `bmad-review-edge-case-hunter` skill. diff --git a/src/bmm-skills/4-implementation/bmad-quick-dev/step-04-review.md b/src/bmm-skills/4-implementation/bmad-quick-dev/step-04-review.md index 2d96fd25d..3151191d8 100644 --- a/src/bmm-skills/4-implementation/bmad-quick-dev/step-04-review.md +++ b/src/bmm-skills/4-implementation/bmad-quick-dev/step-04-review.md @@ -25,7 +25,7 @@ Do NOT `git add` anything — this is read-only inspection. Launch three subagents without conversation context. If no sub-agents are available, generate three review prompt files in `{implementation_artifacts}` — one per reviewer role below — and HALT. Ask the human to run each in a separate session (ideally a different LLM) and paste back the findings. -- **Blind hunter** — receives `{diff_output}` only. No spec, no context docs, no project access. Invoke via the `bmad-review-adversarial-general` skill. +- **Blind hunter** — receives inline `{diff_output}` only. No spec, no context docs, no project access. Invoke via the `bmad-review-adversarial-general` skill. - **Edge case hunter** — receives `{diff_output}` and read access to the project. Invoke via the `bmad-review-edge-case-hunter` skill. - **Acceptance auditor** — receives `{diff_output}`, `{spec_file}`, and read access to the project. Must also read the docs listed in `{spec_file}` frontmatter `context`. Checks for violations of acceptance criteria, rules, and principles from the spec and context docs.