@hopla/claude-setup 1.12.0 → 1.14.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude-plugin/marketplace.json +1 -1
- package/.claude-plugin/plugin.json +1 -1
- package/README.md +239 -180
- package/agents/system-reviewer.md +13 -0
- package/cli.js +284 -399
- package/commands/execute.md +22 -3
- package/commands/guide.md +6 -0
- package/commands/init-project.md +9 -7
- package/commands/plan-feature.md +16 -0
- package/commands/rca.md +7 -2
- package/global-rules.md +18 -50
- package/hooks/session-prime.js +39 -12
- package/package.json +1 -1
- package/skills/brainstorm/SKILL.md +5 -0
- package/skills/code-review/SKILL.md +3 -1
- package/skills/debug/SKILL.md +8 -0
- package/skills/execution-report/SKILL.md +1 -1
- package/skills/git/commit.md +20 -3
- package/skills/git/flow-detection.md +68 -0
- package/skills/git/pr.md +46 -16
- package/skills/verify/SKILL.md +10 -0
- package/skills/worktree/SKILL.md +83 -38
- package/commands/end-to-end.md +0 -67
- package/commands/git-commit.md +0 -76
- package/commands/git-pr.md +0 -138
|
@@ -15,6 +15,7 @@ You are a System Reviewer. Your job is to analyze how well the implementation ma
|
|
|
15
15
|
- **Good divergence**: Found a better approach, justified deviation
|
|
16
16
|
- **Bad divergence**: Missed requirements, ignored constraints, skipped steps
|
|
17
17
|
5. **Trace root causes** — Why did each divergence happen?
|
|
18
|
+
5.5. **Check recommendation history** — Read the 3 most recent system reviews in `.agents/system-reviews/`. If a recommendation appears in 2+ previous reviews and hasn't been applied, flag it as **RECURRING — NOT APPLIED** with escalation priority.
|
|
18
19
|
6. **Suggest improvements** — What should change to prevent bad divergences?
|
|
19
20
|
|
|
20
21
|
## Improvement Decision Matrix
|
|
@@ -60,4 +61,16 @@ Save to `.agents/system-reviews/[feature-name].md`:
|
|
|
60
61
|
|
|
61
62
|
## Key Learnings
|
|
62
63
|
- [Insights worth remembering]
|
|
64
|
+
|
|
65
|
+
## Recommendation Tracking
|
|
66
|
+
|
|
67
|
+
For each recommendation from the 2 most recent system reviews:
|
|
68
|
+
- Was it applied? (Check CLAUDE.md, commands, guides for the suggested change)
|
|
69
|
+
- If not applied, why? (Forgotten, deprioritized, or superseded?)
|
|
70
|
+
- **Recurring unapplied recommendations indicate a broken feedback loop** — escalate these by listing them first in "Recommended Improvements" with a ⚠️ prefix
|
|
71
|
+
|
|
72
|
+
## Next Step
|
|
73
|
+
|
|
74
|
+
After the review is saved, suggest:
|
|
75
|
+
> "System review saved to `.agents/system-reviews/[feature]-review.md`. Plan archived. If recurring recommendations were found, consider applying them before the next feature — they represent known gaps in the process."
|
|
63
76
|
```
|