# audit_batch

Audit code for quality issues. Two modes: pass file_paths (paths or globs like

Agent View of the PolicyLayer registry record for `audit_batch`. HTML page: https://policylayer.com/tools/20alexl-claude-engram/audit-batch

## Facts

- Tool: `audit_batch`
- Server: Claude Engram (`20alexl/claude-engram`) — https://policylayer.com/tools/20alexl-claude-engram.md
- Homepage: https://github.com/20alexl/claude-engram
- Risk category: Read (Low risk)
- Registry record: grade D, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "audit_batch",
    "arguments": {}
  }
}
```

## Why audit_batch is rated Low

Auditing code for quality issues is a read-only operation—it analyzes and reports findings without side effects. No data is modified, deleted, or executed. The tool retrieves information about code quality but does not alter the codebase or trigger external operations. This falls squarely in the 'Read' category with low severity risk.

From the tool's own definition: "Tool name 'audit_batch' and description 'Audit code for quality issues' indicates static analysis/inspection of code. The action is to examine and report on code quality without modifying, deleting, or executing code."

## Use case

AI agents call audit_batch to retrieve information from Claude Engram without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Claude Engram:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "audit_batch": {}
  }
}
```

## Other tools on Claude Engram (15)

- `claude_engram_status` — Read — https://policylayer.com/tools/20alexl-claude-engram/claude-engram-status.md
- `context` — Read — https://policylayer.com/tools/20alexl-claude-engram/context.md
- `convention` — Read — https://policylayer.com/tools/20alexl-claude-engram/convention.md
- `deps_map` — Read — https://policylayer.com/tools/20alexl-claude-engram/deps-map.md
- `file_summarize` — Read — https://policylayer.com/tools/20alexl-claude-engram/file-summarize.md
- `find_similar_issues` — Read — https://policylayer.com/tools/20alexl-claude-engram/find-similar-issues.md
- `impact_analyze` — Read — https://policylayer.com/tools/20alexl-claude-engram/impact-analyze.md
- `memory` — Read — https://policylayer.com/tools/20alexl-claude-engram/memory.md
- `pre_edit_check` — Read — https://policylayer.com/tools/20alexl-claude-engram/pre-edit-check.md
- `scope` — Read — https://policylayer.com/tools/20alexl-claude-engram/scope.md
- `scout_search` — Read — https://policylayer.com/tools/20alexl-claude-engram/scout-search.md
- `session_end` — Read — https://policylayer.com/tools/20alexl-claude-engram/session-end.md
- `session_mine` — Read — https://policylayer.com/tools/20alexl-claude-engram/session-mine.md
- `session_start` — Read — https://policylayer.com/tools/20alexl-claude-engram/session-start.md
- `work` — Read — https://policylayer.com/tools/20alexl-claude-engram/work.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=20alexl-claude-engram · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/20alexl-claude-engram