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 skills add adampoit/ai --skill agents-mdgit clone --depth 1 https://github.com/adampoit/aiWrote 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/skills/adampoit/ai/agents-md)<a href="https://agentmods.dev/skills/adampoit/ai/agents-md"><img src="https://agentmods.dev/badge/skills/adampoit/ai/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/adampoit/ai/agents-md"><img src="https://agentmods.dev/badge/skills/adampoit/ai/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00055 | $0.01454 |
| Opus 5.5 | $0.00022 | $0.00582 |
| Sonnet 5.5 | $0.00011 | $0.00291 |
| Haiku 4.5 | $0.00006 | $0.00145 |
Grade A, and why
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 1mo 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents Md
AGENTS.md is a README for AI agents: a dedicated place to provide context and instructions to help AI coding agents work effectively on a project.
Important: Keep It Minimal
Key principle: Include only what agents cannot infer from the codebase itself. Redundant documentation is harmful—agents already read files, search code, and understand common patterns.
When to Create/Update
- Create: When the project has non-obvious tooling, specific commands, or critical boundaries agents must know
- Update: When commands change, new critical constraints are added, or tooling requirements evolve
- Omit: If your repository has standard structure and common tooling (React, Python, etc.) that agents already understand
What to Include
Focus only on information agents cannot discover themselves:
1. Essential Commands (Required)
Specific commands with full flags. Include only if non-standard or critical.
## Commands
- Install: `pnpm install`
- Dev: `pnpm dev --port 3000`
- Test: `pnpm test --coverage`
- Build: `pnpm build`
Skip this section if using standard commands (e.g., npm install, npm test).
2. Tooling Requirements (If Non-Standard)
Specify tools agents should use. Research shows agents DO follow specific tool instructions (e.g., uv usage increases 1.6x when mentioned).
## Tooling
- Use `uv` for Python dependency management
- Use `ruff` for linting (not flake8)
- Use `just` for task running (not Make)
Only include if different from defaults agents would assume.
3. Boundaries (Critical)
What agents must NEVER do. This is the highest-value content.
## Boundaries
- Never commit secrets, API keys, or `.env` files
- Never modify `vendor/`, `node_modules/`, or lock files
- Never remove failing tests—fix or ask first
- Ask before changing database schemas
Always include this section. It prevents costly mistakes.
4. Project-Specific Patterns (If Unusual)
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 237 lines · 55 tokens per session scan A 51b1985ff84b
agents-md is a skill published in the GitHub repository adampoit/ai (2 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,454 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
agent-platform-prompt-management
Manages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent Platform. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform prompts.
gemini-api-dev
Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, speech generation (TTS), voice design, voice replication, streaming responses, background research tasks, function calling, structured output, or migrating from…
ml-kit-genai-prompt-api
Analyzes Android codebases to implement ML Kit GenAI Prompt API. Use this skill to send natural language requests on-device to Gemini Nano, use structured output with Prompt API, implement prefix caching, optimize the current prompt, or apply best practices.".
nowait-reasoning-optimizer
Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens"…
huashu-prompt-save
A filing tool that identifies the type of a prompt and saves it under categories such as technical, content, teaching, product, or general.
seats-aero
Search award flight availability across 27 mileage programs via Seats.aero Partner API. Find cheapest award flights, compare programs, and get booking links.