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 instructions/stacklok/toolhive-registry-server/claude-mdgit clone --depth 1 https://github.com/stacklok/toolhive-registry-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/instructions/stacklok/toolhive-registry-server/claude-md)<a href="https://agentmods.dev/instructions/stacklok/toolhive-registry-server/claude-md"><img src="https://agentmods.dev/badge/instructions/stacklok/toolhive-registry-server/claude-md.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 | $0.02470 | $0.02470 |
| Opus 5 | $0.01235 | $0.01235 |
| Sonnet 5 | $0.00494 | $0.00494 |
| Haiku 4.5 | $0.00247 | $0.00247 |
Grade A, and why
toolhive-registry-server 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 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides AI assistant guidance for working with the ToolHive Registry API Server codebase.
Design Rules
Scoped design rules live in .claude/rules/. Each file has a paths: frontmatter glob and is auto-loaded when Claude Code is working on files that match. They cover layering, the data model, auth/claims, the API surface (admin vs upstream spec), the sync pipeline, and secrets handling. Read the rule file that matches the area you're changing, and cite it by section when reviewing a PR that conflicts with one (e.g. "this violates auth.md §3 — uniform claim matching").
Available Subagents
Registry Server uses specialized AI subagents for different aspects of development. These agents are configured in .claude/agents/ and MUST be invoked when you need to perform tasks that come under their expertise:
Core Development Agents
-
golang-code-writer: Expert Go developer for writing clean, idiomatic Go code. Use when creating new functions, structs, interfaces, or complete packages.
-
unit-test-writer: Specialized in writing comprehensive unit tests for Go code. Use when you need thorough test coverage for functions, methods, or components.
-
code-reviewer: Reviews code for Registry Server best practices, security patterns, Go conventions, and architectural consistency. Use after significant code changes. Should cross-check changes against the matching rule file under
.claude/rules/. -
tech-lead-orchestrator: Provides architectural oversight, task delegation, and technical leadership for code development projects. Use for complex features or architectural decisions.
Support Agents
- security-advisor: Provides security guidance for coding tasks, including code reviews, architecture decisions, and secure implementation patterns.
When to Use Subagents
Invoke specialized agents when:
- You need expertise in their specific domain (e.g., writing code, reviewing code)
- Writing new code (use golang-code-writer)
- Creating tests (use unit-test-writer)
- Orchestrating the different tasks to other subagents that are required for completing work asked by the user (use tech-lead-orchestrator)
- Reviewing code that is written (use code-reviewer)
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 · 172 lines · 2,470 tokens per session scan A 979f65ca1b65
toolhive-registry-server CLAUDE.md is an instructions file published in the GitHub repository stacklok/toolhive-registry-server (24 stars, last pushed today), licensed Apache-2.0. It adds 2,470 tokens to every session, about $0.0123 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.
Other instructions, from other repositories
pipelock AGENTS.md
AGENTS.md instructions for luckyPipewrench/pipelock, covering agents.md - pipelock contributor guide, quick reference, capability surface, build, test, lint and architecture.
gate CLAUDE.md
Instructions for GaaraZhu/gate, covering gate, notes, repository structure, build and test commands and before every commit.
tooltrust-scanner CLAUDE.md
Claude Code instructions for AgentSafe-AI/tooltrust-scanner: Use the /browse skill from gstack for all web browsing. Never use mcpclaude-in-chrome tools.
claude-skills CLAUDE.md
Instructions for mastepanoski/claude-skills, covering claude.md, repository purpose, testing skills locally, repository architecture and core structure.
ai-act-companion copilot-instructions.md
Copilot instructions for JKasteele/ai-act-companion, covering github copilot instructions — ai act companion, what this is, the one architectural invariant — do not break it, using the engine via mcp and commands.
ai-act-companion CLAUDE.md
Claude Code instructions for JKasteele/ai-act-companion, covering claude.md, what this is, commands, setup and run the web app.