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/fenwei-dev/mcp2skill/agents-mdgit clone --depth 1 https://github.com/fenwei-dev/mcp2skillWhat 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 | $0.01173 | $0.01173 |
| Opus 5 | $0.00587 | $0.00587 |
| Sonnet 5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
mcp2skill AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding assistants working in this repository.
Project Overview
mcp2skill is a Go CLI tool that converts MCP (Model Context Protocol) servers into agent skills. It generates skill packages with SKILL.md documentation from MCP server metadata.
Build, Lint, and Test Commands
# Build
go build ./cmd/mcp2skill # Standard build
CGO_ENABLED=0 go build -ldflags="-s -w" ./cmd/mcp2skill # Static binary for distribution
# Run all tests
go test ./...
# Run tests with coverage
go test -cover ./...
# Run a single test file
go test -v ./internal/config
# Run a single test function
go test -v -run TestFunctionName ./internal/config
# Run tests in specific package with timeout
go test -timeout 30s ./internal/mcp
# Lint (if golangci-lint is installed)
golangci-lint run ./...
golangci-lint run --new-from-rev HEAD~1 # Lint only changes
Code Style Guidelines
Formatting
- Use
gofmt(orgo fmt) to format code before committing - Run
go vetto catch common mistakes - Configure editor to format on save with gofmt
Imports
- Use standard Go import organization with
go fmt/goimports - Group imports: standard library first, then third-party, then internal
- Use dot imports sparingly (only in test files when helpful)
Types and Interfaces
- Use struct types for data containers with JSON tags for config files
- Define interfaces for external dependencies (e.g., MCP client) to enable testing
- Prefer concrete types over interfaces unless mocking is needed
- Use type aliases for domain-specific strings (e.g.,
type TransportType string)
Naming Conventions
- Packages: lowercase, short, descriptive (e.g.,
config,mcp,cliapp) - Exported identifiers: PascalCase (e.g.,
LoadEffective,ServerConfig) - Unexported identifiers: camelCase (e.g.,
loadEffective,serverCfg) - Variables: concise but descriptive; avoid single letters except loop indices
- Constants: SNAKE_CASE for grouped constants, PascalCase for exported enums
- Acronyms: Use consistent casing (e.g.,
ServeMux, notServeMIXorServeMuxID)
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.
- 2d ago First seen · 134 lines · 1,173 tokens per session scan A df088295187d
mcp2skill AGENTS.md is an instructions file published in the GitHub repository fenwei-dev/mcp2skill (55 stars, last pushed 7mo ago), licensed MIT. It adds 1,173 tokens to every session, about $0.0059 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.