# Dejavu Scan

> Trigger a manual scan for antipatterns. Use when user asks "scan for patterns", "dejavu scan", "check for mistakes".

- **Type:** Skill
- **Install:** `agentstack add skill-cmg8431-claude-dejavu-dejavu-scan`
- **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-scan
- **Website:** https://www.npmjs.com/package/claude-dejavu

## Install

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

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

## About

# claude-dejavu: Manual Scan

You are triggering a manual antipattern scan with claude-dejavu.

## Steps

1. Run the scan command:

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

2. Present the results to the user:
   - How many sessions were analyzed
   - New patterns detected (if any)
   - Rules proposed or updated
   - Any changes applied to CLAUDE.md

3. If new rules were proposed, show them and ask the user whether to approve:

```
Found 2 new patterns:

  [proposed] "Always use pnpm, not npm, in this project."
  confidence: 0.85 | evidence: 3 sessions

  [proposed] "Run type-check before committing TypeScript changes."
  confidence: 0.72 | evidence: 2 sessions

Approve these rules? [y/n/edit]
```

4. If no new patterns were found, reassure the user:

```
No new antipatterns detected. Your current rules look good.
```

## Important

- Always show what the scan found, even if it found nothing
- Let the user decide whether to approve proposed rules
- If the scan fails, show the error and suggest checking that claude-dejavu is installed correctly

## 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-scan
- 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%.