bchanot/claude
1
0
Fork 1
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(model-routing): SDD implementation + review subagents dispatched model sonnet

Browse Source
This commit is contained in:
Bastien Chanot
2026-07-15 11:40:42 +02:00
parent 56c451ea25
commit 0fbe3103cb
2 changed files with 12 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/init-project/SKILL.md
+6
View File
@@ -176,6 +176,12 @@ Invoke `superpowers:subagent-driven-development` for the per-task implement loop
`gitflow finish` (STEP 11). When SDD's flow reaches "Use `gitflow finish` (STEP 11). When SDD's flow reaches "Use
finishing-a-development-branch", stop and return. finishing-a-development-branch", stop and return.
**Model routing (BDR-066):** every subagent dispatched under SDD — per-task
implementers AND its reviewers — MUST carry `model: "sonnet"` in the Agent
call. The plan is closed; execution and plan-conformity review are sonnet
work. Reflection (task decomposition, review verdict arbitration) stays in
this loop.
## STEP 8b — GRAPHIFY FULL (after implementation) ## STEP 8b — GRAPHIFY FULL (after implementation)
If `graphify` CLI is installed AND complexity >= 30%: If `graphify` CLI is installed AND complexity >= 30%:
1. Run full graphify on the implemented project: 1. Run full graphify on the implemented project:
skills/ship-feature/SKILL.md
+6
View File
@@ -154,6 +154,12 @@ Invoke `superpowers:subagent-driven-development` for the per-task implement loop
`gitflow finish` (STEP 9). When SDD's flow reaches "Use `gitflow finish` (STEP 9). When SDD's flow reaches "Use
finishing-a-development-branch", stop and return. finishing-a-development-branch", stop and return.
**Model routing (BDR-066):** every subagent dispatched under SDD — per-task
implementers AND its reviewers — MUST carry `model: "sonnet"` in the Agent
call. The plan is closed; execution and plan-conformity review are sonnet
work. Reflection (task decomposition, review verdict arbitration) stays in
this loop.
## STEP 4b — ERROR RECOVERY (if STEP 4 fails) ## STEP 4b — ERROR RECOVERY (if STEP 4 fails)
If a subagent returns a build error, failing test, or type error: If a subagent returns a build error, failing test, or type error:
1. Load `$HOME/.claude/agents/analyzer.md` in DEBUG MODE on the exact error output. 1. Load `$HOME/.claude/agents/analyzer.md` in DEBUG MODE on the exact error output.