quartermaster-retrieve-tools

quartermaster-retrieve-tools is a skill for Claude Code from PranavNagrecha/Quartermaster. It costs 38 tokens per session (322 once invoked), scanned A, original, MIT.

Instructions for finding MCP tools through Quartermaster, a router that exposes tools from multiple MCP servers. It uses a search step to choose the right downstream tool before calling it.

In plain words
What is it for?
For discovering tools with a natural-language query, checking the router's confidence, calling a selected namespaced tool, and diagnosing missing or degraded server connections.
Why use it?
It avoids loading every available tool description and helps select the relevant tool when many servers are connected.

Skill for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

Part of the quartermaster plugin — 1 skill shipped together

Good fit For discovering tools with a natural-language query, checking the router's confidence, calling a selected namespaced tool, and diagnosing missing or degraded server connections.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pranavnagrecha/quartermaster/quartermaster-retrieve-tools
Install

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.

Any agent
npx skills add PranavNagrecha/Quartermaster --skill quartermaster-retrieve-tools
Clone the repo
git clone --depth 1 https://github.com/PranavNagrecha/Quartermaster

Made for: Claude Code.

Or install quartermaster, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for quartermaster-retrieve-tools

README.md
[![agentmods](https://agentmods.dev/badge/skills/pranavnagrecha/quartermaster/quartermaster-retrieve-tools/github.svg)](https://agentmods.dev/skills/pranavnagrecha/quartermaster/quartermaster-retrieve-tools)
Your own site
<a href="https://agentmods.dev/skills/pranavnagrecha/quartermaster/quartermaster-retrieve-tools"><img src="https://agentmods.dev/badge/skills/pranavnagrecha/quartermaster/quartermaster-retrieve-tools/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.

agentmods 80×15 button for quartermaster-retrieve-tools

Your own site · 80×15
<a href="https://agentmods.dev/skills/pranavnagrecha/quartermaster/quartermaster-retrieve-tools"><img src="https://agentmods.dev/badge/skills/pranavnagrecha/quartermaster/quartermaster-retrieve-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 322 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.00322
Opus 5 $0.00019 $0.00161
Sonnet 5 $0.00008 $0.00064
Haiku 4.5 $0.00004 $0.00032

Measured 11d ago against content hash 76320e4d44f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

quartermaster-retrieve-tools 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 11d 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.

.claude-plugin/skills/quartermaster-retrieve-tools/SKILL.md · 31 lines

What it actually says

Quartermaster tool discovery

When quartermaster-mcp is configured as an MCP server, use its meta-tools instead of loading all downstream tools.

Workflow

  1. Call retrieve_tools with a natural-language query describing what the user wants to do.
  2. Read the JSON response: candidates (ranked tools with descriptions and inputSchema), confidence, and guidance.
  3. If confidence is low or none, ask the user to clarify or rephrase before calling a tool.
  4. Call call_tool with the chosen namespaced tool name (e.g. github.create_issue) and its arguments.
  5. Use list_servers when debugging — check degraded and skipped if routing seems incomplete.

Example

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: { ... } })

Notes

  • Do not assume tools exist without checking retrieve_tools first — downstream manifests change.
  • Prefer guidance in the response when confidence is not high.
  • Set QM_DEBUG=1 on the proxy process to log scores to stderr when tuning synonyms.
Changes

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.

  1. 11d ago First seen · 31 lines · 38 tokens per session scan A 76320e4d44f2

Subscribe to this mod's changes

quartermaster-retrieve-tools is a skill published in the GitHub repository PranavNagrecha/Quartermaster (0 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 322 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

mle-workflow

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

affaan-m/ECC · 44 tokens

autonomous-loops

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

affaan-m/ECC · 26 tokens

react-patterns

React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.

affaan-m/ECC · 49 tokens

content-engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

affaan-m/ECC · 55 tokens

article-writing

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

affaan-m/ECC · 57 tokens

agent-carnet

Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.

yamadashy/repomix · 67 tokens