copilot-security-instructions: Agent for Claude Code

.github/agents/mcp-tool-author.agent.md

mcp-tool-author is an agent for Claude Code from Robotti-io/copilot-security-instructions. It costs 29 tokens per session (227 once invoked), scanned A, original, Apache-2.0.

A coding agent that builds and updates MCP tools, prompts, and resources in a project's source folder. MCP is a standard way for an AI assistant to call tools and access structured information.

In plain words
What is it for?
Use it when adding or refactoring MCP tools, prompts, or resources, then checking them with example calls.
Why use it?
It helps keep tool names, input rules, outputs, exports, and server registration consistent. It also reduces the risk of unclear or unstable tool interfaces.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is Robotti-io/copilot-security-instructions's own configuration. It tells Claude Code how to work on copilot-security-instructions itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything copilot-security-instructions configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Robotti-io/copilot-security-instructions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Robotti-io/copilot-security-instructions/main/.github/agents/mcp-tool-author.agent.md
Clone the repo
git clone --depth 1 https://github.com/Robotti-io/copilot-security-instructions

Made for: Claude Code.

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 mcp-tool-author

README.md
[![agentmods](https://agentmods.dev/badge/agents/robotti-io/copilot-security-instructions/mcp-tool-author.svg)](https://agentmods.dev/agents/robotti-io/copilot-security-instructions/mcp-tool-author)
Your own site
<a href="https://agentmods.dev/agents/robotti-io/copilot-security-instructions/mcp-tool-author"><img src="https://agentmods.dev/badge/agents/robotti-io/copilot-security-instructions/mcp-tool-author.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 227 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 $0.00029 $0.00227
Opus 5 $0.00015 $0.00113
Sonnet 5 $0.00006 $0.00045
Haiku 4.5 $0.00003 $0.00023

Measured 7d ago against content hash 06994c27dd23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-tool-author 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 7d 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.

.github/agents/mcp-tool-author.agent.md · 28 lines

What it actually says

You build MCP tools and related assets.

Scope

  • src/mcp_tools/*
  • src/mcp_prompts/*
  • src/mcp_resources/*

Rules

  • Every tool MUST have:
    • stable tool name (consistent casing and separators)
    • clear title + description
    • zod input schema (even if empty)
    • deterministic output shape
  • Prefer returning structured, parseable text (JSON string is ok when explicitly intended).
  • Do not leak secrets or include large file contents unless explicitly requested.
  • Update exports (src/mcp_tools/index.js) and registration (src/mcp_server.js) as needed.

Output format

  • What tool/resource/prompt you added/changed
  • Exact file edits (full content for changed files)
  • Quick manual test steps (example tool call payloads)
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. 7d ago First seen · 28 lines · 29 tokens per session scan A 06994c27dd23

Subscribe to this mod's changes

mcp-tool-author is an agent published in the GitHub repository Robotti-io/copilot-security-instructions (42 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 227 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 2026-08-30.