front-mcp AGENTS.md

front-mcp AGENTS.md is an instructions file for Codex, OpenCode from wearehoust/front-mcp. It costs 2,120 tokens per session, scanned A, original, MIT.

A repository instruction file for a TypeScript MCP server. MCP is a way for an agent to call external tools and access services.

In plain words
What is it for?
It is for guiding work on the Front integration, including its tools, API services, authentication, policies, schemas, tests, and documentation.
Why use it?
It gives contributors one place to learn the project’s purpose, structure, safety rules, setup, and verification practices before changing code.

Instructions file for CodexOpenCode

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/wearehoust/front-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/wearehoust/front-mcp

Made for: Codex, OpenCode.

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 front-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wearehoust/front-mcp/agents-md.svg)](https://agentmods.dev/instructions/wearehoust/front-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/wearehoust/front-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/wearehoust/front-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,120 This file is loaded in full into every session.
When invoked 2,120 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 $0.02120 $0.02120
Opus 5 $0.01060 $0.01060
Sonnet 5 $0.00424 $0.00424
Haiku 4.5 $0.00212 $0.00212

Measured 4d ago against content hash 0406c543ad80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

front-mcp 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 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.

AGENTS.md · 134 lines

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.

Repository guidance

Purpose

This strict TypeScript MCP server exposes Front resources over stdio, validates inputs with Zod, and applies policy, sanitization, logging, rate-limit, retry, and authentication controls.

Front operations can create, update, assign, send, import, merge, grant, remove, and delete. Treat every non-read action as an external mutation requiring explicit user authority regardless of policy.

Architecture

  • src/index.ts owns CLI handling, configuration, authentication selection, diagnostics, and stdio.
  • src/server.ts constructs services, registers all tools, and binds MCP request handlers.
  • src/tools/ validates tool arguments, evaluates policy, and formats/sanitizes responses.
  • src/services/ maps resource actions to Front API requests.
  • src/client/ owns HTTP, OAuth, token storage, retry, and rate limiting.
  • src/policy/default-policy.ts classifies actions; src/policy/engine.ts resolves decisions.
  • src/schemas/ is the Zod contract for Front resources and tool inputs.
  • tests/unit/ and tests/integration/ use mocks; scripts/live-test*.js contact a real Front account.
  • docs/TOOL_REFERENCE.md is generated by scripts/generate-tool-docs.js.

Preserve the dependency direction tools -> services -> client; lower layers must not import upward.

Setup and verification

Use Node 20 or newer. CI uses the committed lockfile and runs:

npm ci
npm run lint
npm run type-check
npm test
npm run build
npm run smoke
  • Run focused Vitest files while iterating, then the relevant full gates.
  • npm run build compiles TypeScript and runs the postbuild script.
  • npm run smoke expects dist/index.js already to exist; the package script does not build first.
  • npm run generate-docs overwrites docs/TOOL_REFERENCE.md; review it when its sources change.
  • Do not install dependencies or execute gates when the task is instruction-only.

Implementation conventions

  • Keep TypeScript strict; do not add any, ts-ignore, or stdout logging.
  • stdout is reserved for MCP protocol messages; use the repository logger, which writes to stderr.
  • Add tests for every behavior change, including schema, service, tool, and policy layers as affected.
  • New resources need a policy classification, schema, service, tool registration, server registration, and corresponding tests.
  • Keep exact dependency pins unless a deliberate upgrade validates all supported Node versions.
  • Preserve HTTPS-only requests, retry/rate-limit behavior, token-file permissions, redaction, and sanitization boundaries.

Read the full file on GitHub · 134 lines

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. 4d ago First seen · 134 lines · 2,120 tokens per session scan A 0406c543ad80

Subscribe to this mod's changes

front-mcp AGENTS.md is an instructions file published in the GitHub repository wearehoust/front-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 2,120 tokens to every session, about $0.0106 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 2026-08-31.