agentmods.dev

toolhive-catalog CLAUDE.md

Repository instructions for ToolHive Catalog, a curated directory of MCP servers and skills. They describe the registry layout, validation commands, and rules for adding catalog entries.

In plain words
What is it for?
Use them when adding or reviewing MCP servers or skills, validating catalog files, building catalog output, or running Go tests and linters.
Why use it?
They help an agent make catalog changes that match the repository’s structure and pass its checks.

Instructions file

21 5d ago A scan 377 tokens original Apache-2.0
View the source file stacklok/toolhive-catalog
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.

agentmods
npx agentmods add instructions/stacklok/toolhive-catalog/claude-md
Clone the repo
git clone --depth 1 https://github.com/stacklok/toolhive-catalog
Per session 377 This file is loaded in full into every session.
When invoked 377 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00377 $0.00377
Opus 5 $0.00188 $0.00188
Sonnet 5 $0.00075 $0.00075
Haiku 4.5 $0.00038 $0.00038

Measured 2d ago against content hash cca1dedb9611, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

toolhive-catalog CLAUDE.md 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 2d 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.md · 42 lines

What it actually says

toolhive-catalog

Curated registry of MCP (Model Context Protocol) servers and skills for ToolHive.

Skills

  • /add-mcp-server — use when adding a new server entry to the catalog
  • /mcp-review — use when reviewing a PR that adds or updates a server entry

Key commands

Uses Taskfile, not Make:

task catalog:validate   # validate all server.json files
task catalog:build      # build the catalog output
task test               # run Go tests
task lint               # run linters

Registry structure

Each server lives at registries/toolhive/servers/<name>/ containing:

  • server.json — server definition (see docs/adding-entries-llm.md for full schema)
  • icon.svg — server icon

Each skill lives at registries/toolhive/skills/<name>/ containing:

  • skill.json — skill definition (uses Skill type from toolhive-core)
  • icon.svg — skill icon
  • skill/ — subfolder with installable content (SKILL.md, scripts/, references/, assets/)
    • The packages[].subfolder in skill.json points here so only skill content is installed, not registry metadata

Non-obvious gotchas

  • The _meta extension key must exactly match packages[0].identifier or remotes[0].url
  • metadata.* and tool_definitions are auto-populated by CI — never add them manually
  • Commits require a Signed-off-by trailer (DCO)

Go code

CLI entry point: cmd/catalog/. Packages: internal/. Requires Go 1.25+.

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. 2d ago First seen · 42 lines · 377 tokens per session scan A cca1dedb9611

Subscribe to this mod's changes

toolhive-catalog CLAUDE.md is an instructions file published in the GitHub repository stacklok/toolhive-catalog (21 stars, last pushed 5d ago), licensed Apache-2.0. It adds 377 tokens to every session, about $0.0019 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 2026-08-30.

Building agentscatalogmcpmodel-context-protocolregistry
Related

Other instructions, from other repositories

obsidian-mcp-server AGENTS.md

Instructions for cyanheads/obsidian-mcp-server, covering agent protocol, what's next?, core rules, patterns and tool — obsidianlisttags.

cyanheads/obsidian-mcp-server · 6,725 tokens

MCP-Nest CLAUDE.md

Instructions for rekog-labs/MCP-Nest, covering claude.md, what this repo is, packages, layout and commands.

rekog-labs/MCP-Nest · 916 tokens

mcp-server-apple-events GEMINI.md

Gemini CLI instructions for FradSer/mcp-server-apple-events, covering apple events mcp server, project overview, architecture, building and running and prerequisites.

FradSer/mcp-server-apple-events · 1,136 tokens

dcc-mcp-maya GEMINI.md

Instructions for dcc-mcp/dcc-mcp-maya, covering gemini.md — google gemini / vertex ai integration guide, what this project does, gemini-specific strengths, 1. skill script generation and 2. structured tool results.

dcc-mcp/dcc-mcp-maya · 652 tokens

hass-mcp-server AGENTS.md

Instructions for ganhammar/hass-mcp-server, covering working on this integration, calling into home assistant, before replacing a private call with a service, anything left in category 2 or 3 and conventions.

ganhammar/hass-mcp-server · 636 tokens

minecraft-dev-mcp CLAUDE.md

Instructions for MCDxAI/minecraft-dev-mcp, covering claude code context - minecraft dev mcp, project overview, release status, architecture and core services (src/services/).

MCDxAI/minecraft-dev-mcp · 5,815 tokens