Borrowing it
Nothing to install: this file belongs to agigante80/actual-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/agigante80/actual-mcp-server/main/.claude/commands/dep-auditor.mdgit clone --depth 1 https://github.com/agigante80/actual-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/agigante80/actual-mcp-server/dep-auditor)<a href="https://agentmods.dev/commands/agigante80/actual-mcp-server/dep-auditor"><img src="https://agentmods.dev/badge/commands/agigante80/actual-mcp-server/dep-auditor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/agigante80/actual-mcp-server/dep-auditor"><img src="https://agentmods.dev/badge/commands/agigante80/actual-mcp-server/dep-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02061 |
| Opus 5 | $0.00000 | $0.01030 |
| Sonnet 5 | $0.00000 | $0.00412 |
| Haiku 4.5 | $0.00000 | $0.00206 |
Grade A, and why
dep-auditor scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://api.npmjs.org/downloads/point/last-week/<pkg>" # weekly downloads How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run a dependency health audit for actual-mcp-server and create GitHub issues for any findings.
Usage
Accepted arguments: [--full]
- Default: skip libraries checked within the last 30 days (cache-first)
--full: ignore the cache and re-audit every library
Overview
Runs 4 sequential checks, writes results to docs/audit/dep-audit-cache.json, and opens GitHub issues for every finding. Never auto-removes or auto-updates anything — create tickets only.
Step 1 — Read the cache
Read docs/audit/dep-audit-cache.json if it exists. Structure:
{
"lastFullAudit": "<ISO timestamp>",
"libraries": {
"<package-name>": {
"lastChecked": "<YYYY-MM-DD>",
"status": "maintained|unmaintained|deprecated",
"lastPublish": "<YYYY-MM-DD>",
"weeklyDownloads": 0
}
}
}
If the file does not exist, treat all libraries as uncached. If --full was passed, treat all libraries as uncached regardless.
Step 2 — Check 1: Unused dependencies (Knip)
Knip is now committed and configured (#234): use the project config, not bare npx knip.
npm run knip 2>&1 # uses the committed knip.json (report-only)
Scope split (#234): this auditor owns DEPENDENCY findings only (unused or duplicate
package.json entries). The unused FILES, EXPORTS, and TYPES that Knip also reports are
SOURCE dead code, owned by the /code-health-auditor skill. Do NOT file source dead-code
tickets here; leave them to /code-health-auditor.
Known false positives — exclude from tickets:
tsconfig-paths— used byscripts/register-tsconfig-paths.jsat runtimedotenv— loaded dynamically viasrc/index.ts@types/*packages — compile-time only, not detectable by Knip@playwright/test— test-only, conditionally executed
For any remaining unused DEPENDENCY flagged by Knip (not exports/files: those go to /code-health-auditor), prepare one ticket:
Title:
fix: remove unused dependencies (Knip)Labels:infrastructureBody: list each flagged item with the file/import path where it appears (or doesn't)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 253 lines · 0 tokens per session scan A c2490cb2f479
dep-auditor is a command published in the GitHub repository agigante80/actual-mcp-server (54 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,061 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
security-review
A security review procedure based on CWE, a list of common software weaknesses, and STRIDE, a method for identifying threats to a system.
version
Display current guide and Claude Code versions.
diff-docs
Compare official Anthropic docs baseline vs current snapshot (no network — instant).
docs-review
Phase 4 of documenting-projects: Quality gate with 8 measurable criteria and iteration. Triggers: '/docs-review', invoked by documenting-projects orchestrator.
review-a11y
Review the current branch for accessibility (WCAG 2.1 AA) and responsive behavior in a React/Next.js codebase. Supports whole-branch review or scoped review by path, feature, or base branch.
review-arch
Review the current branch for code quality, TypeScript, and React/Next.js patterns. Supports whole-branch review or scoped review by path, feature, or base branch.