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/mcp360/mtarsier/agents-mdgit clone --depth 1 https://github.com/mcp360/mTarsierWhat 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 | $0.01413 | $0.01413 |
| Opus 5 | $0.00707 | $0.00707 |
| Sonnet 5 | $0.00283 | $0.00283 |
| Haiku 4.5 | $0.00141 | $0.00141 |
Grade A, and why
mTarsier 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 3d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mTarsier — Agent Guide
Read this before making any changes to the codebase.
Project Overview
mTarsier is a desktop app for managing MCP (Model Context Protocol) servers across all AI clients. Built with Tauri v2 (Rust backend) + React 19 + TypeScript + Tailwind CSS v4 + Zustand.
Key Paths
| Path | Purpose |
|---|---|
src/ |
React frontend |
src/pages/ |
Full-page views (Dashboard, Clients, Config, Marketplace, Settings, About) |
src/components/ |
Shared UI components |
src/components/marketplace/ |
Marketplace-specific components |
src/store/ |
Zustand state stores |
src/lib/ |
Utilities (clients registry, themes, utils) |
src/types/ |
TypeScript types |
src-tauri/src/ |
Rust backend |
src-tauri/src/commands/ |
Tauri commands (config, clients, audit, cli, io, utils) |
src-tauri/src/bin/tsr.rs |
CLI binary entry point |
src-tauri/scripts/ |
Build helper scripts |
src-tauri/binaries/ |
Compiled sidecar binaries (gitignored, generated by prepare-sidecar.sh) |
Architecture
React UI ──invoke()──▶ Tauri Commands (Rust) ──▶ Filesystem / OS
│
▼
app_lib (shared Rust lib)
│
▼
tsr CLI binary (clap)
Frontend Conventions
- Styling: Tailwind CSS v4 with custom design tokens in
src/index.css - State: Zustand stores in
src/store/—clientStore,configStore,themeStore,settingsStore - Tauri calls: Always use
invoke<T>("command_name", { args })with try/catch - Themes: Colors accessed via CSS variables (
text-primary,bg-surface,text-text-muted, etc.) - Component size: Keep under 150 lines — extract if larger
Design Tokens
| Token | Value | Usage |
|---|---|---|
primary |
#00ff88 |
Accent, active states, success |
cyan |
#00d4ff |
Secondary accent |
amber |
#ffb800 |
Warnings, hints |
base |
#080c0a |
Page background |
surface |
slightly lighter | Cards, sidebar |
border |
subtle | Borders |
text-muted |
muted | Secondary text |
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.
- 3d ago First seen · 141 lines · 1,413 tokens per session scan A a17cbcde1f0e
mTarsier AGENTS.md is an instructions file published in the GitHub repository mcp360/mTarsier (49 stars, last pushed 4mo ago), licensed MIT. It adds 1,413 tokens to every session, about $0.0071 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
mcpscore AGENTS.md
Instructions for mcp-box/mcpscore, covering agent instructions for mcpscore and gotchas (learned the hard way).
pixabay-mcp-server CLAUDE.md
Claude Code instructions for hanoak/pixabay-mcp-server, covering claude.md, project overview, tech stack (decided — do not relitigate without discussion), architecture & folder conventions and coding standards.
zaezd AGENTS.md
AGENTS.md instructions for EvilFreelancer/zaezd, covering zaezd - agent brief, state of the repository, commands, how work is delivered and layers.
metmuseum-mcp CLAUDE.md
Instructions for mikechao/metmuseum-mcp, covering claude.md, project overview, development commands, install dependencies (requires pnpm) and type checking.
metmuseum-mcp AGENTS.md
Instructions for mikechao/metmuseum-mcp, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
brick-mcp-app CLAUDE.md
Instructions for dend/brick-mcp-app, covering brick builder mcp app, important rules, specs, tech stack and key commands.