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/shekarsiri/moo-tasks/agents-mdgit clone --depth 1 https://github.com/shekarsiri/moo-tasksWrote 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/shekarsiri/moo-tasks/agents-md)<a href="https://agentmods.dev/instructions/shekarsiri/moo-tasks/agents-md"><img src="https://agentmods.dev/badge/instructions/shekarsiri/moo-tasks/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 5.1 | $0.00867 | $0.00867 |
| Opus 5 | $0.00434 | $0.00434 |
| Sonnet 5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00087 | $0.00087 |
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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- moo-tasks CLAUDE.md — 92% identical, 5 lines differ
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🐮 AGENT GUIDELINES & PROTOCOL (Moo Tasks)
⚠️ CRITICAL DIRECTIVE: You are connected to the Moo Tasks MCP server. For EVERY user instruction, bug fix, or feature request, you MUST record and track your work in Moo Tasks with FULL TECHNICAL DETAILS BEFORE modifying code or running terminal commands. Never edit code without an active claimed task ID.
⚡ 1-Call Fast-Path for Rapid Coding (Recommended)
When the user asks you to implement a feature or fix an issue, use moo_quick_start to atomically create and claim the task in a single step with complete specifications:
{
"title": "Implement feature X",
"type": "feature",
"tags": ["backend", "api"],
"description": "### Technical Overview\nDetailed design, architectural breakdown, and step-by-step implementation plan.\n\n### Implementation Plan\n1. Step 1...\n2. Step 2...",
"acceptanceCriteria": "- [ ] Clear, testable markdown definition of done\n- [ ] Unit tests pass",
"priority": "high",
"declaredFiles": ["src/feature.ts"]
}
🎯 Full Mandatory 6-Step Workflow Protocol
1. Goal Anchoring (Prevent Scope Drift)
- Always anchor the human user's overarching request with
moo_create_goal(title, verbatimPrompt, description). - Always include:
- verbatimPrompt: Store the user's EXACT verbatim prompt to maintain fidelity.
- description: Full rich Markdown PRD, architectural breakdown, component boundaries, and milestones.
2. Task Planning & Full Specifications
- Break down the goal into small, atomic tasks before touching code:
- Call
moo_create_taskormoo_create_tasks_batch. - Task titles must be clean, descriptive text — do NOT embed priority codes, category prefixes, or sequence numbers in titles (e.g. avoid
"C1: …","H2: …","UX-3: …","M1 — …"). Use thepriority,type, andtagsfields for classification. - ALWAYS write a comprehensive
descriptioncontaining:- Technical Overview & Architecture: Why and how this is built.
- Step-by-Step Implementation Plan: Numbered actionable steps.
- Design Decisions / Code Snippets: Key types, schemas, or endpoints.
- ALWAYS write testable
acceptanceCriteriain Markdown with checkboxes (- [ ]) BEFORE touching code. - Declare
declaredFilesand prerequisitedependsOnTaskIds(DAG cycle prevention is enforced). - Open tasks cap (max 10 open items per goal) is strictly enforced to prevent over-planning.
- Call
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.
- 5d ago First seen · 64 lines · 867 tokens per session scan A 7f151bb7c443
moo-tasks AGENTS.md is an instructions file published in the GitHub repository shekarsiri/moo-tasks (2 stars, last pushed 16d ago), licensed MIT. It adds 867 tokens to every session, about $0.0043 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
enquire-mcp AGENTS.md
AGENTS.md instructions for oomkapwn/enquire-mcp, covering agents.md, tl;dr, architecture (5-minute orientation), conventions and typescript.
repo-context-mcp AGENTS.md
Instructions for nduc99911/repo-context-mcp, covering agents.md — repo-context-mcp, project, layout, commands and conventions.
toon-memory AGENTS.md
Instructions for LuiggiVal08/toon-memory, covering agents.md, build & verify, architecture, smarter memory pattern and visual memory pattern.
social0-mcp AGENTS.md
AGENTS.md instructions for Abhishek-B-R/social0-mcp, covering agents.md — social0 mcp, what this is, setup checklist, tool reference and listaccounts.
mcp-yandex-audience CLAUDE.md
Claude Code instructions for A1-x-Tech/mcp-yandex-audience, covering claude.md — mcp-yandex-audience, commands, architecture, conventions (do not break) and adding a tool.
mcp-yandex-merchants CLAUDE.md
Claude Code instructions for A1-x-Tech/mcp-yandex-merchants, covering claude.md — mcp-yandex-merchants, commands, architecture, conventions (do not break) and adding a tool.