BMAD-METHOD/src/bmm-skills
PinkyD fdd65dc3d9
fix(skills): pass diff output inline to the blind-hunter reviewer (#2463)
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 <noreply@anthropic.com>
2026-06-10 11:23:26 -05:00
..
1-analysis fix(skills): strengthen activation guardrails to prevent LLM short-circuiting (#2398) 2026-05-25 09:59:38 -05:00
2-plan-workflows fix(skills): strengthen activation guardrails to prevent LLM short-circuiting (#2398) 2026-05-25 09:59:38 -05:00
3-solutioning fix(bmad-create-epics-and-stories): discover bmad-ux spine outputs (#2446) 2026-06-06 20:32:47 -05:00
4-implementation fix(skills): pass diff output inline to the blind-hunter reviewer (#2463) 2026-06-10 11:23:26 -05:00
module-help.csv refactor(bmad-ux): spine-based UX skill (DESIGN.md + EXPERIENCE.md) (#2413) 2026-05-22 23:16:06 -05:00
module.yaml v6.7.0: bundle module registry, retire marketplace, refresh display names (#2388) 2026-05-17 17:47:25 -05:00