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

fix(ce-work): make code review invocation mandatory by default (#453)

Browse Source 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Trevin Chow
2026-03-30 01:31:17 -07:00
committed by GitHub
parent 638b38abd2
commit 7f3aba29e8
2 changed files with 16 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
plugins/compound-engineering/skills/ce-work/SKILL.md
View File

@@ -282,18 +282,18 @@ Determine how to proceed based on what was provided in `<input_document>`.
# Use linting-agent before pushing to origin
```
2. **Code Review**
2. **Code Review** (REQUIRED)
Every change gets reviewed before shipping. The depth scales with the change's risk profile.
Every change gets reviewed before shipping. The depth scales with the change's risk profile, but review itself is never skipped.
**Tier 1: Inline self-review** — Read the diff and check for logic errors, missed edge cases, and plan drift. No specialized agents. Use this tier only when **all four** criteria are true:
**Tier 2: Full review (default)** — REQUIRED unless Tier 1 criteria are explicitly met. Invoke the `ce:review` skill with `mode:autofix` to run specialized reviewer agents, auto-apply safe fixes, and surface residual work as todos. When the plan file path is known, pass it as `plan:<path>`. This is the mandatory default — proceed to Tier 1 only after confirming every criterion below.
**Tier 1: Inline self-review** — A lighter alternative permitted only when **all four** criteria are true. Before choosing Tier 1, explicitly state which criteria apply and why. If any criterion is uncertain, use Tier 2.
- Purely additive (new files only, no existing behavior modified)
- Single concern (one skill, one component — not cross-cutting)
- Pattern-following (implementation mirrors an existing example with no novel logic)
- Plan-faithful (no scope growth, no deferred questions resolved with surprising answers)
**Tier 2: Full review (default)** — Load the `ce:review` skill with `mode:autofix` to run specialized reviewer agents, auto-apply safe fixes, and surface residual work as todos. When the plan file path is known, pass it as `plan:<path>`. This is the default when working from a plan — use it unless all four Tier 1 criteria are met.
3. **Final Validation**
- All tasks marked completed
- Testing addressed -- tests pass and new/changed behavior has corresponding test coverage (or an explicit justification for why tests are not needed)
@@ -455,14 +455,14 @@ Before creating PR, verify:
Every change gets reviewed. The tier determines depth, not whether review happens.
**Tier 1 (inline self-review)** — all four must be true:
**Tier 2 (full review)** — REQUIRED default. Invoke `ce:review mode:autofix` with `plan:<path>` when available. Safe fixes are applied automatically; residual work surfaces as todos. Always use this tier unless all four Tier 1 criteria are explicitly confirmed.
**Tier 1 (inline self-review)** — permitted only when all four are true (state each explicitly before choosing):
- Purely additive (new files only, no existing behavior modified)
- Single concern (one skill, one component — not cross-cutting)
- Pattern-following (mirrors an existing example, no novel logic)
- Plan-faithful (no scope growth, no surprising deferred-question resolutions)
**Tier 2 (full review)** — the default when working from a plan. Invoke `ce:review mode:autofix` with `plan:<path>` when available. Safe fixes are applied automatically; residual work surfaces as todos.
## Common Pitfalls to Avoid
- **Analysis paralysis** - Don't overthink, read the plan and execute