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/xonika9/agent-skills/agents-mdgit clone --depth 1 https://github.com/xonika9/agent-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/xonika9/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/xonika9/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/xonika9/agent-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 | $0.00779 | $0.00779 |
| Opus 5 | $0.00390 | $0.00390 |
| Sonnet 5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
agent-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 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.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Skills repository
This is the public source of truth for the x9-* Agent Skills. The package targets the open Agent Skills format; Claude Code and Codex also have native plugin manifests in this repository. Never create branches — always commit and work directly on main.
Source ownership
- Treat every directory under
skills/as canonical. Do not create runtime-specific copies of a skill. - Keep platform-specific behavior inside a clearly named adapter or reference. Do not claim portability for a route that depends on a missing runtime tool.
- The installable global-instruction files live under
global-files/<harness>/. They do not govern work on this repository; the rootAGENTS.mdremains canonical here. - Preserve unrelated and user-owned changes. Never commit, push, create a tag, or publish a release unless the user explicitly requests it.
README and public copy
- Keep
README.mdas the canonical English presentation andREADME.ru.mdas its Russian localization. Update the English structure first, then keep the Russian version materially equivalent. - Explain skills through the problem they solve and the result a user gets. Keep the first screen useful before adding detail.
- Keep the Telegram call to action near the top of both READMEs and keep the
x9-prefix explanation discoverable. - Do not hard-code the number of skills in prose; the contents of
skills/change over time. - Do not publish placeholder screenshots or fabricated demos. Keep recording instructions under
docs/until a real, sanitized capture is ready. - Keep the repository hero and social preview at
assets/x9-agent-skills-hero.jpgin a 2:1 layout. Keep plugin identity assets underassets/and validate every path declared in a manifest. - GitHub social preview is a repository setting, not a README side effect. After an explicitly authorized visual update, upload the hero in Settings and verify the rendered repository card.
- After editing Russian public copy, run the
humanizer-ruscanner. If its optional Python packages are unavailable, use an ephemeral environment rather than changing global Python state. - Keep sensitive data, personal paths, credentials, browser profiles, cookies, and tokens out of the repository.
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 · 41 lines · 779 tokens per session scan A 70823a040d83
agent-skills AGENTS.md is an instructions file published in the GitHub repository xonika9/agent-skills (4 stars, last pushed 8d ago), licensed MIT. It adds 779 tokens to every session, about $0.0039 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
playwright-rust CLAUDE.md
Instructions for padamson/playwright-rust, covering claude.md, project, repository layout, skills (procedural reference) and documentation hierarchy.
browser-agent CLAUDE.md
Instructions for uiuing/browser-agent, a project described as: An open-source AI agent for the browser. Bring any model. It plans in the side panel, acts on real pages through tools, and verifies every claimed result against the live DOM — with guardrails and reusable skills.
nika AGENTS.md
AGENTS.md instructions for supernovae-st/nika, covering agents — nika diamond, repository snapshot, what to read first, hard rules (non-negotiable) and crate admission: 12 gates.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
bxc GEMINI.md
Instructions for aphrody-code/bxc: This repository's operating guide is CLAUDE.md — read it first.
AIPex CLAUDE.md
Instructions for AIPexStudio/AIPex, a project described as: AIPex: AI browser automation assistant, no migration and privacy first. Alternative to Manus Browser Operator、 Claude Chrome and Agent Browser.