# 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".

- **Type:** Skill
- **Install:** `agentstack add skill-cmg8431-claude-dejavu-dejavu`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [cmg8431](https://agentstack.voostack.com/s/cmg8431)
- **Installs:** 0
- **Category:** [Databases](https://agentstack.voostack.com/c/databases)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [cmg8431](https://github.com/cmg8431)
- **Source:** https://github.com/cmg8431/claude-dejavu/tree/main/plugin/skills/dejavu
- **Website:** https://www.npmjs.com/package/claude-dejavu

## Install

```sh
agentstack add skill-cmg8431-claude-dejavu-dejavu
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# claude-dejavu: Review Learned Rules

You are helping the user review antipattern rules that claude-dejavu has detected from past sessions.

## Steps

1. First, run the dejavu binary to get current status:

```bash
claude-dejavu stats --path "$(pwd)"
```

2. Then list all rules:

```bash
claude-dejavu list --path "$(pwd)"
```

3. 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

4. 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]                                 │
└───────────────────────────────────────────────────┘
```

5. If the user approves, apply rules to CLAUDE.md:

```bash
claude-dejavu scan --path "$(pwd)"
```

6. 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](https://github.com/cmg8431)
- **Source:** [cmg8431/claude-dejavu](https://github.com/cmg8431/claude-dejavu)
- **License:** MIT
- **Homepage:** https://www.npmjs.com/package/claude-dejavu

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-cmg8431-claude-dejavu-dejavu
- Seller: https://agentstack.voostack.com/s/cmg8431
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.