john/claude-engineering-plugin
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(review): harden ce-review base resolution (#452)

Browse Source
This commit is contained in:
Trevin Chow
2026-03-30 01:10:45 -07:00
committed by GitHub
parent e872e15efa
commit 638b38abd2
5 changed files with 331 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
plugins/compound-engineering/skills/ce-review/SKILL.md
View File

@@ -338,6 +338,8 @@ If a plan is found, read its **Requirements Trace** (R1, R2, etc.) and **Impleme
Read the diff and file list from Stage 1. The 4 always-on personas and 2 CE always-on agents are automatic. For each cross-cutting and stack-specific conditional persona in the persona catalog included below, decide whether the diff warrants it. This is agent judgment, not keyword matching.
**`previous-comments` is PR-only.** Only select this persona when Stage 1 gathered PR metadata (PR number or URL was provided as an argument, or `gh pr view` returned metadata for the current branch). Skip it entirely for standalone branch reviews with no associated PR -- there are no prior comments to check.
Stack-specific personas are additive. A Rails UI change may warrant `kieran-rails` plus `julik-frontend-races`; a TypeScript API diff may warrant `kieran-typescript` plus `api-contract` and `reliability`.
For CE conditional agents, check if the diff includes files matching `db/migrate/*.rb`, `db/schema.rb`, or data backfill scripts.
@@ -376,11 +378,7 @@ Pass the resulting path list to the `project-standards` persona inside a `<stand
Persona sub-agents do focused, scoped work and should use cheaper/faster models to reduce cost and latency. The orchestrator itself stays on the default (most capable) model.
| Platform | Persona agent model | How to set |
|----------|-------------------|------------|
| **Claude Code** | Haiku | Pass `model: "haiku"` in the Agent tool call |
| **Codex** | GPT-4o mini | Set the model parameter to `gpt-4o-mini` in the agent spawn config |
| **Other platforms** | Cheapest capable model available | Use the platform's equivalent of a fast/cheap tier |
Use the platform's cheapest capable model for all persona and CE sub-agents. In Claude Code, pass `model: "haiku"` in the Agent tool call. On other platforms, use the equivalent fast/cheap tier (e.g., `gpt-4o-mini` in Codex). If the platform has no model override mechanism or the available model names are unknown, omit the model parameter and let agents inherit the default -- a working review on the parent model is better than a broken dispatch from an unrecognized model name.
CE always-on agents (agent-native-reviewer, learnings-researcher) and CE conditional agents (schema-drift-detector, deployment-verification-agent) also use the cheaper model tier since they perform scoped, focused work.