Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/sembraniteam/claude-plugins/audit-depsgit clone --depth 1 https://github.com/sembraniteam/claude-pluginsWrote 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/sembraniteam/claude-plugins/audit-deps)<a href="https://agentmods.dev/commands/sembraniteam/claude-plugins/audit-deps"><img src="https://agentmods.dev/badge/commands/sembraniteam/claude-plugins/audit-deps.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.00643 |
| Opus 5 | $0.00014 | $0.00321 |
| Sonnet 5 | $0.00006 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
audit-deps scanned grade A with 0 findings 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 4d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are scanning project dependencies for known CVEs using the security-auditor plugin's vuln-lookup MCP server.
Step 1 — Discover all manifest files
Search the project for dependency manifests:
package.json,package-lock.json,yarn.lock,pnpm-lock.yaml(npm/Node)requirements.txt,Pipfile,Pipfile.lock,pyproject.toml,poetry.lock(Python)go.mod,go.sum(Go)pom.xml,build.gradle,build.gradle.kts(Java/Kotlin)Cargo.toml,Cargo.lock(Rust)composer.json,composer.lock(PHP)Gemfile,Gemfile.lock(Ruby)*.csproj,packages.config,*.nuspec(C#/.NET)
List the manifests found before proceeding.
Step 2 — Extract pinned versions
For each manifest:
- Parse the exact version currently installed (from the lockfile if available — lockfiles have the real pinned version, unlike
package.jsonranges) - Build a list of
(ecosystem, package_name, version)tuples
Step 3 — Query OSV.dev for each package
For each (ecosystem, package, version):
- Call
query_osv(ecosystem=..., package=..., version=...)via thevuln-lookupMCP server - If OSV returns vulnerabilities with CVE aliases, call
get_cve(cve_id)on each to get CVSS score and severity from NVD
RULE: Never write a CVE number that was not returned by one of these MCP tool calls. If OSV returns no results, the row in the output table shows "None found".
Step 4 — Output the results table
For each package that has at least one CVE, output a row:
| Package | Installed | CVE | CVSS | Severity | Fixed In |
|---------|-----------|-----|------|----------|----------|
| lodash | 4.17.4 | CVE-2019-10744 | 9.8 | Critical | 4.17.21 |
After the table with vulnerable packages, add a short section:
Clean packages (no CVEs found): list them in a compact format, e.g., [email protected] ✓, [email protected] ✓.
Step 5 — Priority recommendation
List the top 3 most urgent updates based on CVSS score, with the exact upgrade command:
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.
- 4d ago First seen · 59 lines · 28 tokens per session scan A 0268868c73c6
audit-deps is a command published in the GitHub repository sembraniteam/claude-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 643 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.