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/yschimke/skills/agents-mdgit clone --depth 1 https://github.com/yschimke/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/yschimke/skills/agents-md)<a href="https://agentmods.dev/instructions/yschimke/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/yschimke/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 | $0.00555 | $0.00555 |
| Opus 5 | $0.00278 | $0.00278 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
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 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI agents (Claude Code, Codex, Gemini, etc.) working in this repo.
This is a content-only repo. The skills here are markdown documentation
that pairs with the compose-preview CLI and Gradle plugin published from
yschimke/compose-ai-tools.
The CLI lives there; consumer guidance lives here.
When adding, renaming, or removing a skill
- Update
README.md— keep the skills list in sync. Each entry links to the skill'sSKILL.mdand summarises what it covers. If you add a skill and don't update the README, the change is incomplete. - Do not bump the plugin version unless explicitly asked. When you
are asked for a release, edit
.claude-plugin/plugin.jsonusing semver: patch for wording/docs, minor for a new skill or new triggers, major for removals or breaking renames.
Skill layout
- Skills live at
skills/<skill-name>/SKILL.md. Flat — never nest by topic. Encode the topic in the directory name (e.g.compose-preview-review, notcompose-preview/review). - The
name:in the SKILL.md frontmatter must match the directory name exactly. Use lowercase kebab-case for both. - Supporting files (design notes, scripts) sit alongside
SKILL.mdin the skill dir.
Manifests
.claude-plugin/marketplace.jsonand.claude-plugin/plugin.jsonare both JSON (not JSONC). Validate withjq . <file>before committing.- The plugin
namein both manifests must stayyschimke-skills.
Cross-repo references
The compose-preview skill documents the CLI shipped from the
compose-ai-tools repo, so it cites release tags (e.g.
v1.3.0) and links into that repo. Keep those links stable. When the
CLI gets a new version, update referenced version strings here; do not
introduce a release-please marker in this repo — versions in skill text
track the upstream CLI, not this plugin.
What not to do
- Don't add CI, build tooling, or Gradle config here — this is a content
repo. CI, packaging, and the renderer live in
compose-ai-tools. - Don't rename existing skill directories "for consistency" without a concrete reason; renames break user references and bundled installs.
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 · 52 lines · 555 tokens per session scan A e75f593fb557
skills AGENTS.md is an instructions file published in the GitHub repository yschimke/skills (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 555 tokens to every session, about $0.0028 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
android-clean-template AGENTS.md
AGENTS.md instructions for mykola-kichatov/android-clean-template, covering agents.md, fresh clone?, build & development commands, architecture and domain layer.
android-clean-template CLAUDE.md
Claude Code instructions for mykola-kichatov/android-clean-template, a project described as: It's a typical list-detail app. Simple Android app template utilizing Jetpack Compose, suitable for creating general Android native apps.
Amarok-Hider AGENTS.md
Instructions for deltazefiro/Amarok-Hider, covering amarok, project overview, build, e2e test and agent rules.
sceneview AGENTS.md
AGENTS.md instructions for sceneview/sceneview, covering agents.md — conventions for delegated coding agents, your role, git — you do not own it, secrets and hard technical rules.
AppClaw CLAUDE.md
Claude Code instructions for appclawhq/AppClaw, covering claude.md, what is appclaw?, build & run commands, architecture and entry point & cli modes (src/index.ts).
FDEOps AGENTS.md
Instructions for suboss87/FDEOps, covering agents.md - working in the fdeops repository, if you are helping use fdeops in an engagement, if you are contributing to this repository and boundaries.