quartermaster-retrieve-tools — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited quartermaster-retrieve-tools (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
When quartermaster-mcp is configured as an MCP server, use its meta-tools instead of loading all downstream tools.
retrieve_tools with a natural-language query describing what the user wants to do.candidates (ranked tools with descriptions and inputSchema), confidence, and guidance.confidence is low or none, ask the user to clarify or rephrase before calling a tool.call_tool with the chosen namespaced tool name (e.g. github.create_issue) and its arguments.list_servers when debugging — check degraded and skipped if routing seems incomplete.retrieve_tools({ query: "open a bug on the repository", k: 8 })
→ read candidates[0] (likely github.create_issue)
call_tool({ name: "github.create_issue", arguments: { ... } })retrieve_tools first — downstream manifests change.guidance in the response when confidence is not high.QM_DEBUG=1 on the proxy process to log scores to stderr when tuning synonyms.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.