Dejavu
Review and manage learned antipattern rules. Use when Claude should review its past mistakes, apply learned rules to CLAUDE.md, or check rule effectiveness. Triggers on "/dejavu", "review rules", "what did you learn".
Install
$ agentstack add skill-cmg8431-claude-dejavu-dejavu ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-cmg8431-claude-dejavu-dejavu) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
claude-dejavu: Review Learned Rules
You are helping the user review antipattern rules that claude-dejavu has detected from past sessions.
Steps
- First, run the dejavu binary to get current status:
claude-dejavu stats --path "$(pwd)"- Then list all rules:
claude-dejavu list --path "$(pwd)"- Present the rules to the user in a clear format:
For each rule, show:
- Rule ID and status (active/proposed/dead)
- Rule text — what Claude should do differently
- Detector type — how it was discovered (revert cycle / repeated error / silent fix)
- Confidence and fire count
- Action options: keep, edit, or remove
- If there are proposed rules, ask the user to approve them:
┌─ Proposed rule r-001 ─ [repeated error] ─────────┐
│ "This project uses pnpm, not npm." │
│ Evidence: 4 sessions, last 2 weeks │
│ Confidence: 0.91 │
│ Apply? [y/n/edit] │
└───────────────────────────────────────────────────┘- If the user approves, apply rules to CLAUDE.md:
claude-dejavu scan --path "$(pwd)"- After applying, show a summary of what changed in CLAUDE.md.
Important
- Never modify rules without user confirmation
- Dead rules (no fires in 14+ days) should be suggested for removal
- Rules with high fire counts are valuable — highlight them
- If no rules exist yet, explain that dejavu needs more sessions to detect patterns
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: cmg8431
- Source: cmg8431/claude-dejavu
- License: MIT
- Homepage: https://www.npmjs.com/package/claude-dejavu
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.