frontmcp AGENTS.md

Repository instructions for developing agentfront/frontmcp, a TypeScript framework for the Model Context Protocol (MCP), which lets AI clients use tools and services.

In plain words
What is it for?
Use it when editing this repository, installing dependencies, running the demo, building packages, linting, writing tests, or deciding where authentication code belongs.
Why use it?
It keeps changes consistent with the project’s monorepo structure, TypeScript rules, authentication boundaries, naming conventions, and test commands. A monorepo is one repository containing multiple related packages or applications.

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/agentfront/frontmcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/agentfront/frontmcp

Made for: Codex, OpenCode.

Per session 408 This file is loaded in full into every session.
When invoked 408 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 $0.00408 $0.00408
Opus 5 $0.00204 $0.00204
Sonnet 5 $0.00082 $0.00082
Haiku 4.5 $0.00041 $0.00041

Measured yesterday against content hash 6eb2ff3b524a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontmcp 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 yesterday.

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 · 33 lines

What it actually says

  • This repository is an Nx-based TypeScript monorepo.
  • Package manager: yarn.
  • Workspaces live under apps/*, libs/*, and plugins/*.
  • Primary publishable libraries are under the @frontmcp/* scope.
  • libs/sdk: core FrontMCP SDK.
  • libs/cli: command-line interface.
  • libs/adapters: framework adapters and integrations.
  • libs/plugins: plugin system and extensions.
  • libs/auth: authentication, session management, credential vault, CIMD, and OAuth extensions.
  • apps/demo: demo application for development and testing.
  • Prefer minimal, focused changes.
  • Follow existing TypeScript patterns and keep strict typing.
  • Do not introduce any without clear justification.
  • For MCP protocol outputs, prefer concrete MCP result types rather than unknown.
  • Keep auth-related code in libs/auth, not libs/sdk.
  • Test files must use .spec.ts or .spec.tsx naming.
  • Avoid legacy or compatibility re-exports in barrel files.
  • Install dependencies: yarn install
  • Run demo app: yarn dev
  • Build all projects: yarn build
  • Lint all projects: yarn lint
  • Run all tests: yarn test
  • Run unit tests: yarn test:unit
  • Run e2e tests: yarn test:e2e
  • Run Playwright tests: yarn test:pw
  • Maintain strict TypeScript correctness.
  • Keep builds free of warnings where possible.
  • Preserve or improve test coverage for touched code.
  • Do not make unrelated refactors while addressing a focused task.
  • node_modules is already present in the workspace.
  • Generated outputs such as dist, coverage, tmp, perf-results, and test-results are already ignored by git.
  • Check for more specific instructions in nested AGENTS.md files before editing subdirectories.
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. yesterday First seen · 33 lines · 408 tokens per session scan A 6eb2ff3b524a

Subscribe to this mod's changes

frontmcp AGENTS.md is an instructions file published in the GitHub repository agentfront/frontmcp (147 stars, last pushed 25d ago), licensed Apache-2.0. It adds 408 tokens to every session, about $0.0020 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.