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/focus-mcp/cli/agents-mdgit clone --depth 1 https://github.com/focus-mcp/cliWhat 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 | $0.02711 | $0.02711 |
| Opus 5 | $0.01355 | $0.01355 |
| Sonnet 5 | $0.00542 | $0.00542 |
| Haiku 4.5 | $0.00271 | $0.00271 |
Grade A, and why
cli 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.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is the single source of truth for AI agent behavior on this project. It follows the agents.md standard and is read by Claude Code, Cursor, Aider, GitHub Copilot, and any other AI coding tool.
Humans, this file is for you too — it documents our conventions and expectations.
Project
FocusMCP CLI — the primary entry point of FocusMCP. Published as @focus-mcp/cli on npm.
This repo is the primary entry point: a Node CLI that embeds @focus-mcp/core and speaks stdio MCP (via @modelcontextprotocol/sdk) to AI clients (Claude Code, Cursor, Codex, Gemini CLI…).
Read VISION.md for the complete CLI vision (commands, transport, distribution).
Ecosystem
| Repo | Status | Role |
|---|---|---|
focus-mcp/core |
active | TS monorepo lib — 3 pillars (Registry/EventBus/Router) + SDK/Validator/Marketplace resolver. Consumed via file:../core/packages/core. |
focus-mcp/cli (here) |
active | @focus-mcp/cli — stdio MCP, brick manager (focus list/info/add/remove/search/catalog/browse). Published on npm. |
focus-mcp/marketplace |
active | Official catalog + bricks/* + modules/*. |
focus-mcp/client |
archived | Former Tauri desktop app, frozen after CLI-first pivot. |
CLI-first architecture
AI client (Claude Code, Cursor, Codex, Gemini…)
│ stdio (JSON-RPC / MCP)
▼
@focus-mcp/cli (focus start)
├─ @modelcontextprotocol/sdk StdioServerTransport
├─ @focus-mcp/core (createFocusMcp)
│ Registry + EventBus + Router + bricks
└─ ~/.focus/center.json + ~/.focus/center.lock
focus start is the only way AI clients attach. Do not add HTTP as the default transport; do not bundle a UI. A separate cli-manager (Phase 2) will consume a future admin API if needed.
Distribution: npm install -g @focus-mcp/cli or npx @focus-mcp/cli start.
Claude Code native plugin
The repo ships a native Claude Code plugin in .claude-plugin/plugin.json (v1.1.0):
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.
- yesterday First seen · 200 lines · 2,711 tokens per session scan A 011c8fa3d4f7
cli AGENTS.md is an instructions file published in the GitHub repository focus-mcp/cli (0 stars, last pushed 3mo ago), licensed MIT. It adds 2,711 tokens to every session, about $0.0136 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
mirage CLAUDE.md
Instructions for strukto-ai/mirage, covering claude.md, repo layout, typescript packages, python/typescript parity and module layout.
mcp-steroid CLAUDE.md
Instructions for jonnyzzz/mcp-steroid, covering claude.md, agents.md, design philosophy, recursive context lookup (do this before sub-folder work), sub-folder guides and must do.
TakoVM CLAUDE.md
Instructions for Tako-Research/TakoVM, covering tako vm, why gvisor?, architecture, key concepts and build & test.
kinocut copilot-instructions.md
Copilot instructions for KyaniteLabs/kinocut: Read the nearest AGENTS.md for repository rules. For Kinocut workflows, load skills/kinocut/SKILL.md; it is the canonical public skill. Keep this adapter limited to host-specific discovery and do not duplicate policy here.
akm AGENTS.md
Instructions for itlackey/akm, covering akm repo notes, workflow, architecture, tests and test-isolation harness.
trustabl GEMINI.md
Instructions for trustabl/trustabl, a project described as: Fix agent reliability issues across Claude, OpenAI, Google ADK, MCP, LangChain, CrewAI, AutoGen, Pydantic AI, and Vercel AI.