|
14 | 14 | | Medium (multiple files, research needed) | Delegate to Task agent | |
15 | 15 | | Large (new feature, refactor) | Multiple agents in parallel | |
16 | 16 |
|
| 17 | +## Plan Mode |
| 18 | +<!-- rule-id: R-0013, added: 2026-02-23, trigger: Boris Cherny best practices analysis --> |
| 19 | + |
| 20 | +- Enter plan mode for tasks with 3+ steps or architectural decisions |
| 21 | +- If unexpected issues arise during implementation, STOP immediately and re-plan |
| 22 | + |
17 | 23 | ## Forbidden |
18 | 24 | <!-- rule-id: R-0003, added: 2026-01-01, trigger: founding rule --> |
19 | 25 |
|
|
29 | 35 | - Don't "patch symptoms". Show the chain and prove where the value changes. |
30 | 36 | - When fixed, verify with: (1) reproduction steps, (2) a targeted test, (3) typecheck/build. |
31 | 37 |
|
| 38 | +## Quality Gate |
| 39 | +<!-- rule-id: R-0014, added: 2026-02-23, trigger: Boris Cherny best practices analysis --> |
| 40 | + |
| 41 | +- Before completing a task, ask yourself: "Would a staff engineer approve this change?" |
| 42 | +- If NO, do not mark as complete — improve it first |
| 43 | + |
32 | 44 | ## Session exit |
33 | 45 | <!-- rule-id: R-0005, added: 2026-01-01, trigger: founding rule --> |
34 | 46 |
|
@@ -63,13 +75,20 @@ Always cite sources. If unverified, state "unverified". |
63 | 75 | ## Governance |
64 | 76 | <!-- rule-id: R-0010, added: 2026-02-22, trigger: Boris Cherny philosophy implementation --> |
65 | 77 |
|
66 | | -- テスト/ビルド/lint失敗が3回再発したら、governance-proposerでルール提案 |
67 | | -- `/governance-review` を月1回実行してルール鮮度を監査 |
68 | | -- CLAUDE.mdの全ルールにprovenance: `<!-- rule-id: XX, added: YYYY-MM-DD, trigger: description -->` |
| 78 | +- If test/build/lint failures recur 3 times, propose a rule via governance-proposer |
| 79 | +- Run `/governance-review` monthly to audit rule freshness |
| 80 | +- All CLAUDE.md rules must have provenance: `<!-- rule-id: XX, added: YYYY-MM-DD, trigger: description -->` |
| 81 | + |
| 82 | +## Self-Improvement Loop |
| 83 | +<!-- rule-id: R-0012, added: 2026-02-23, trigger: Boris Cherny best practices analysis --> |
| 84 | + |
| 85 | +- When corrected by the user, immediately record the pattern in auto memory |
| 86 | +- Record: what was wrong, the correct pattern, and a prevention rule |
| 87 | +- Check memory at session start to leverage past lessons |
69 | 88 |
|
70 | 89 | ## Simplification |
71 | 90 | <!-- rule-id: R-0011, added: 2026-02-22, trigger: Boris Cherny philosophy implementation --> |
72 | 91 |
|
73 | | -- 単一モジュール: `/simplify-pipeline` |
74 | | -- 複数モジュール: `/refactor-swarm` |
75 | | -- 簡素化は動作を変えない。動作変更は別タスク |
| 92 | +- Single module: `/simplify-pipeline` |
| 93 | +- Multiple modules: `/refactor-swarm` |
| 94 | +- Simplification must not change behavior. Behavior changes are a separate task |
0 commit comments