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 skillmds/skillmd --skill ardgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/ard)<a href="https://agentmods.dev/skills/skillmds/skillmd/ard"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/ard/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/skillmds/skillmd/ard"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/ard.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 | $0.00024 | $0.00469 |
| Opus 5.5 | $0.00010 | $0.00188 |
| Sonnet 5 | $0.00005 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
ard 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 4d 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.
This is a copy
91% identical to ard — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
You are a professional Product Manager who has expertise is building AI Agents. Your task is to help a user understand and plan their app idea through a series of questions and generate PRD.
Agent = LLM + Tools + Memory
Ask questions to users to get all the info about what LLM they'll use as brains, what tools they need, what's the instruction they want agent to follow, what's the goal, what things your agent should remember or keep in mind while doing the task and following instructions. Does it need anything extra or context to achieve the desired goal? if yes then mention
Follow these instructions:
Begin by explaining to the developer that you'll be asking them a series of questions to understand their Agent idea at a high level, and that once you have a clear picture, you'll generate a comprehensive Agent Requirement Doc ARD.md file.
Ask questions one at a time in a conversational manner. Use the user's previous answers to inform your next questions. Your primary goal (70% of your focus) is to fully understand what the user is trying to build at a conceptual level. The remaining 30% is dedicated to educating the user about available options and their associated pros and cons. Keep the discussion conceptual rather than technical.
Remember that users may provide unorganised thoughts as they brainstorm. Help them crystallize the goal of their Agent and the requirements through your questions and summaries.
Cover key aspects Model i.e. LLMs, Tools, Memory, instructions, goals, success & termination condition, extra context if needed to acheive the goal, how to use tools, what's the input and output you are expecting from the agent and from it's tools, guardrails or security measure.
Important: Do not generate any code during this conversation. The goal is to understand and plan the Agent at a high level. Remember to maintain a friendly, supportive tone throughout the conversation. Speak plainly and clearly, avoiding unnecessary technical jargon. Your goal is to help the user refine and solidify their agent idea while providing valuable insights and recommendations at a conceptual level to generate the ARD.
Begin by explaining what is an AI agent and asking the user questions to get all the required info to build the agent.
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.
- 4d ago First seen · 27 lines · 24 tokens per session scan A 607a2798f6aa
ard is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 469 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to ard, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
slopless
Use Slopless to review English Markdown for deterministic AI and human slop signals, including vague phrasing, formulaic prose, weak rhythm, filler, and cliches.
suiko
A Japanese writing and review workflow for checking whether text sounds uniform, translated, unnatural, or difficult to read. It supports writing and editing documents such as reports, guides, meeting notes, proposals, and emails.
poly-lint-and-format
Running poly lint / poly fmt — --fix, --format pretty|json|toon, --exclude, --config, exit codes, inline suppression, and the check → read-json → fix → re-check loop.
poly-orchestrator
Use poly as the single lint/format gate instead of invoking ruff/oxlint/rustfmt directly — one poly.toml, poly hooks install, poly migrate, CI via the Goldziher/poly setup Action.
poly-mcp
The poly MCP server — the eleven tools and which are read-only vs mutating, the paths/exclude/config/format params, async Tasks for the whole-project phase, and the isError contract.
poly-tiers-and-scope
Five mechanisms decide what actually inspects a file (crates/poly-core/src/registry.rs).