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/agentfront/frontmcp/claude-mdgit clone --depth 1 https://github.com/agentfront/frontmcpWhat 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 | $0.05830 | $0.05830 |
| Opus 5 | $0.02915 | $0.02915 |
| Sonnet 5 | $0.01166 | $0.01166 |
| Haiku 4.5 | $0.00583 | $0.00583 |
Grade A, and why
frontmcp 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.
How it starts
The opening of the file, as written. The whole thing — 697 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills and Tools
Auto-generated by
frontmcp skills install(v1.4.0) — do not edit manually.
This project uses FrontMCP skills installed in .claude/skills/.
Before writing code, search the installed skills for relevant guidance:
When you need to implement something, read the matching skill first — it contains patterns, examples, and common mistakes to avoid.
Documentation Site Layout
The Mintlify docs in docs/ are part of the agentfront.dev aggregator site, which serves multiple projects. All FrontMCP pages live under docs/frontmcp/ and ship at https://docs.agentfront.dev/frontmcp/.... Never flatten docs/frontmcp/* into docs/*, never drop the frontmcp/ prefix from docs/docs.json page references, and keep internal MDX links prefixed (e.g. /frontmcp/servers/tools, not /servers/tools). The canonical URL in docs/docs.json must point to https://docs.agentfront.dev/frontmcp.
FrontMCP Monorepo - Development Guide
Repository Structure
- Monorepo: Nx-based monorepo managing multiple TypeScript libraries
- Libraries Location:
/libs/* - each library is independent and publishable
Primary Libraries (scoped under @frontmcp/*)
Located in /libs/*:
- cli (
libs/cli) - Command-line interface - sdk (
libs/sdk) - Core FrontMCP SDK - adapters (
libs/adapters) - Framework adapters and integrations - plugins (
libs/plugins) - Plugin system and extensions - skills (
libs/skills) - Curated SKILL.md catalog for scaffold and install tooling
Note:
ast-guard,vectoriadb,enclave-vm,json-schema-to-zod-v3, andmcp-from-openapihave been moved to external repositories.
Demo Apps
Located in /apps/*:
- demo (
apps/demo) - Demo application for development and testing
Technology Stack
- Build System: Nx (commands:
nx build sdk,nx test ast-guard,nx run-many -t test) - Language: TypeScript with strict mode enabled
- Testing: Jest with 95%+ coverage requirement
- Package Manager: yarn
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 · 697 lines · 5,830 tokens per session scan A 8db304d14b55
frontmcp CLAUDE.md is an instructions file published in the GitHub repository agentfront/frontmcp (147 stars, last pushed 26d ago), licensed Apache-2.0. It adds 5,830 tokens to every session, about $0.0292 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
eve AGENTS.md
Instructions for vercel/eve, covering agents.md, about eve, repository layout, git workflow and commands.
crust AGENTS.md
Instructions for chenxin-yan/crust, covering tests, documentation, changesets, agent skills and issue tracker.
eve CLAUDE.md
Instructions for vercel/eve, a project described as: The Open Framework for Building Agents.
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.
page-agent AGENTS.md
AGENTS.md instructions for alibaba/page-agent, covering instructions for coding assistants, project overview, development commands, architecture and monorepo structure.
oxc AGENTS.md
Instructions for oxc-project/oxc, covering agents.md - ai assistant guide for oxc, ai usage policy for contributors, repository structure, core crates and development commands.