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/dizlexic/moo-tasks/agents-mdgit clone --depth 1 https://github.com/dizlexic/moo-tasksWhat 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 | $0.03550 | $0.03550 |
| Opus 5 | $0.01775 | $0.01775 |
| Sonnet 5 | $0.00710 | $0.00710 |
| Haiku 4.5 | $0.00355 | $0.00355 |
Grade A, and why
moo-tasks 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Drop this file into the root of any project that uses a Moo Tasks board as its task queue. It tells AI coding agents how to discover, accept, and complete work for this repository through the board's MCP server.
1. What is the Moo Tasks board?
Moo Tasks is a kanban board (available at mootasks.dev) that exposes each board as its own Model Context Protocol (MCP) server. The endpoint is scoped to a single board — an agent connected to one board can never see or modify tasks on any other board.
Each task on the board has two identifiers:
-
ID: A unique, permanent string ID (e.g., `A86rlBBUBe3f`) used in tool calls.
-
Board Task ID: A sequential numeric ID specific to the board (e.g., `1`, `2`). Use this for easier reference in conversation.
-
Endpoint URL:
https://mootasks.dev/api/boards/<boardId>/mcp(or your self-hosted host) -
Global Endpoint:
https://mootasks.dev/api/mcp(requires account token) -
Transport:
streamable-http -
Authorization Flow: All requests must include the
Authorizationheader. Use the format:Authorization: Bearer <your-bearer-token>(per MCP basic spec)
⚠️ Tokens via
?token=query string are not supported. Always use theAuthorizationheader.
2. Connecting your agent
On the board page, click Show MCP Config → 📋 Copy JSON. Paste the snippet into your MCP client's config:
{
"mcpServers": {
"moo-tasks": {
"type": "streamable-http",
"url": "https://mootasks.dev/api/boards/<boardId>/mcp",
"headers": {
"Authorization": "Bearer <your-bearer-token>"
}
}
}
}
Common locations:
| Client | Path |
|---|---|
| Claude Code | ~/.claude.json or project .mcp.json |
| Cursor | .cursor/mcp.json |
| VS Code | .vscode/mcp.json |
| JetBrains | Settings → Tools → MCP Servers |
| Junie | Settings → MCP Servers |
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 · 285 lines · 3,550 tokens per session scan A 4494e0e6915c
moo-tasks AGENTS.md is an instructions file published in the GitHub repository dizlexic/moo-tasks (45 stars, last pushed 2mo ago), licensed MIT. It adds 3,550 tokens to every session, about $0.0178 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
agent-device AGENTS.md
AGENTS.md instructions for callstack/agent-device, covering agents.md, incident-derived principles, declaration sites and enforcement, hard repository rules and module and test topology.
agentrq AGENTS.md
Instructions for agentrq/agentrq, covering agentrq codebase notes, project layout, running tests, mcp server (backend/internal/controller/mcp/) and events (experimental).
LeAgent AGENTS.md
Instructions for vixues/LeAgent, covering leagent development guidelines, project overview, architecture, execution topology (one kernel, many ingresses) and surface map (where things live).
claude-code-tresor CLAUDE.md
Instructions for alirezarezvani/claude-code-tresor, covering claude.md - development guide, 🎯 repository purpose, 🏗️ architecture, 🛠️ common development commands and building & testing.
grix AGENTS.md
Instructions for askie/grix, covering grix agent guide, repository boundaries, required workflows, shared agent configuration and cross-component contracts.
rn-dev-agent AGENTS.md
Instructions for Lykhoyda/rn-dev-agent, covering repository guide for agents, repository map, editing rules, architecture rules and supported node runtimes.