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/mimukit/skills/agents-mdgit clone --depth 1 https://github.com/mimukit/skillsWrote 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/mimukit/skills/agents-md)<a href="https://agentmods.dev/instructions/mimukit/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/mimukit/skills/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 | $0.05886 | $0.05886 |
| Opus 5 | $0.02943 | $0.02943 |
| Sonnet 5 | $0.01177 | $0.01177 |
| Haiku 4.5 | $0.00589 | $0.00589 |
Grade A, and why
skills 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 3d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Conventions for AI agents authoring or maintaining skills in this repository — a personal collection of AI agent skills. Follow these whenever you create, rename, or edit a skill.
Skill naming: the kit convention
Every skill uses a kit suffix — a personal brand hidden in the owner's name, mukit, that also reads as "a kit for X."
Rules:
- One word, lowercase, functional term first with
kitappended:commitkit,humankit,prkit. - The functional word must lead so the skill stays searchable — people search
commit, notkit. Never bury the term behind a prefix. - Shorten an awkward root rather than force a clumsy join:
humanize→humankit, nothumanizekit. - Avoid collisions with well-known tools:
speckit(GitHub spec-kit),shipkit(SaaS boilerplate), and anything already popular. - The
name:field in a skill's frontmatter must match its directory name exactly.
Descriptions
A description is a context pointer — it names material the agent isn't holding and encodes the condition for reaching it. Every description in the collection loads on every turn whether or not its skill fires, so the wording does the triggering work and the whole set shares one budget.
- Front-load an English "Use when …" trigger, so agent triggering and text search work regardless of the branded name.
- One trigger per branch, not per synonym. A branch is a distinct case the skill handles, usually a mode. Cover every branch; collapse the phrasings that rename a single one. "teach me X" and "I want to learn X" are one branch written twice, where "teach me X" and "quiz me" are two branches.
- Cut identity the body already carries. A pointer states what the material is and when to reach it. It doesn't restate the skill's rules, its guarantees, or its scope disclaimers.
- Undertriggering is still the expensive failure. Prune synonyms, never coverage — a branch with no trigger silently never fires, and no lint rule can see that.
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.
- 3d ago First seen · 183 lines · 5,886 tokens per session scan A cd26d209e5a4
skills AGENTS.md is an instructions file published in the GitHub repository mimukit/skills (1 stars, last pushed 3d ago), licensed MIT. It adds 5,886 tokens to every session, about $0.0294 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
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.
vibetags com-example-config-AsyncTestConfig.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.
pupila CLAUDE.md
Instructions for FranRom/pupila, covering claude.md, where things live, stack, run locally and repo layout.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.
McpServer AGENTS.md
AGENTS.md instructions for sharpninja/McpServer, covering agent instructions, session start, rules, byrd test gate and where things live.