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/wearehoust/front-mcp/agents-mdgit clone --depth 1 https://github.com/wearehoust/front-mcpWrote 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/wearehoust/front-mcp/agents-md)<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>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 | $0.02120 | $0.02120 |
| Opus 5 | $0.01060 | $0.01060 |
| Sonnet 5 | $0.00424 | $0.00424 |
| Haiku 4.5 | $0.00212 | $0.00212 |
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.
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.tsowns CLI handling, configuration, authentication selection, diagnostics, and stdio.src/server.tsconstructs 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.tsclassifies actions;src/policy/engine.tsresolves decisions.src/schemas/is the Zod contract for Front resources and tool inputs.tests/unit/andtests/integration/use mocks;scripts/live-test*.jscontact a real Front account.docs/TOOL_REFERENCE.mdis generated byscripts/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 buildcompiles TypeScript and runs the postbuild script.npm run smokeexpectsdist/index.jsalready to exist; the package script does not build first.npm run generate-docsoverwritesdocs/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.
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 · 134 lines · 2,120 tokens per session scan A 0406c543ad80
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.
Other instructions, from other repositories
ai-dial-core CLAUDE.md
Claude Code instructions for epam/ai-dial-core, covering claude.md, build & run, set credentials via environment variables, build (skip tests) and run all tests.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).