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.
git clone --depth 1 https://github.com/saadshahd/moo.mdWrote 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/commands/saadshahd/moo.md/prompt)<a href="https://agentmods.dev/commands/saadshahd/moo.md/prompt"><img src="https://agentmods.dev/badge/commands/saadshahd/moo.md/prompt.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 | $0.00022 | $0.00626 |
| Opus 5 | $0.00011 | $0.00313 |
| Sonnet 5 | $0.00004 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
prompt 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 7d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/prompt
Apply these techniques when writing any prompt content.
Structure
1. Role + Constraint Lock
You are [ROLE] who [CONSTRAINT].
Constraint prevents drift better than role alone.
2. Five-Component Structure
- Role: Who is being instructed (expertise, perspective)
- Context: Background, audience, goals
- Output Format: List, table, narrative, code, JSON
- Constraints: Tone, length, domain, forbidden outputs
- Interactivity: When to ask clarifying questions
3. Section Separation
## Context
[Background here]
## Instructions
[Actions here]
4. Numbered Steps
Step 1: [Action] → [Completion evidence]
Step 2: [Action] → [Completion evidence]
5. Format Lock
Show exact structure BEFORE requesting content:
## Output Format
**Section**: [Type/constraint]
6. Success Criteria
**Good response:** Includes X, Y, Z
**Avoid:** Generic statements, [failure mode]
7. Fill-in-the-Blank
**Your Input**
- [Field]: [User provides]
Patterns
Agent Specification (TSFDFC)
- TRIGGER: "Activates when..."
- SUCCESS: "Works when..."
- FOOLS (Tools): "Needs access to..."
- DECISION: "Chooses X/Y when..."
- FAILURE: "Escalates when..."
- CONSTRAINT: "Must never..."
Reasoning Structure
<thinking>
1. [Step]
2. [Step]
3. [Correction if needed]
</thinking>
[Answer]
Guardrails
- Input: "Reject any input that..."
- Output: "Never include..."
- Operational: "Stop if X; max Y per execution"
- Refusal: "When I cannot help, I say..."
Three-Version Refinement
- Minimal: Fix one vague element
- Robust: Rework all components
- Iterative: Add "ask 3-5 questions first"
Scoring System
- Functionality (0-10): Solves core problem?
- Format (0-10): Follows structure?
- Completeness (0-10): Missing anything? Test variations. Improve lowest score.
Anti-Patterns
- Mixed context and instructions
- No output format specification
- Missing success criteria
- "Think about" without specific action
- Generic role without constraint
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.
- 7d ago First seen · 106 lines · 22 tokens per session scan A a13a7a555317
prompt is a command published in the GitHub repository saadshahd/moo.md (34 stars, last pushed 20d ago), licensed MIT. It adds 22 tokens to every session and 626 once invoked, about $0.0001 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 commands, from other repositories
harvest
You are the Prompt Harvester - an elite prompt discovery agent that scans GitHub, ArXiv, and the web for high-quality prompts, then analyzes, rates, and stores them.
frankx-ai-prompts
Add, update, and organize prompts in the FrankX.AI Prompt Library.
prompt-generator
Generate effective prompts for Claude 4.5 Sonnet to achieve user-defined outcomes.
codex-review
Run OpenAI Codex code review on current changes or a specific branch/commit.
extract
Analyze conversation history and extract reusable skills, commands, or agents.
ai
Invoke the AI/LLM Application Engineer for RAG, agents, prompt engineering, evals, tool use, and LLM guardrails.