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/compose-ai-tools/claude-mdgit clone --depth 1 https://github.com/yschimke/compose-ai-toolsWrote 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/compose-ai-tools/claude-md)<a href="https://agentmods.dev/instructions/yschimke/compose-ai-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/yschimke/compose-ai-tools/claude-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 5.1 | $0.00437 | $0.00437 |
| Opus 5 | $0.00218 | $0.00218 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
compose-ai-tools CLAUDE.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 6d 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.
What it actually says
@AGENTS.md
The file above is the repository's canonical agent instructions — the CI-enforced
invariants, the PR workflow, and the map to docs/. Everything below is
Claude-Code-specific harness mechanics that no other agent can act on. Nothing
here restates a rule from AGENTS.md; if the two ever disagree, AGENTS.md wins.
Claude Code
- Repo-local skills live in
.claude/skills/and load on demand rather than on every turn:steward— driving a PR you opened to green: which fast checks to run before pushing, what counts as a failure that is not this PR's, and the check-in loop. Read it before acting on a CI failure or a review comment.render-evidence— capturing the before/after renders a UI-affecting PR needs, including bringing an Android SDK up in a fresh sandbox.flake-triage— proving a preview the diff bot flagged is unstable rather than regressed.
- Subscribe to every PR you open, on the same turn you open it
(
subscribe_pr_activity). Don't ask — tracking is the default; mention it in the reply. Stop on request withunsubscribe_pr_activityand push nothing further to that branch. - Keep a check-in scheduled while a PR you own is red or conflicted
(
send_later, roughly an hour out). Webhook events miss CI successes and merge transitions, so events alone are not enough. Re-arm silently when nothing changed; stop once the PR is merged or closed. <github-webhook-activity>events on tracked PRs are not no-ops. Push the fix when the change is clear and in scope,AskUserQuestionwhen it is ambiguous or architecturally significant, skip silently only for duplicates and echoes of your own comments.stewardhas the full posture.
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.
- 6d ago First seen · 31 lines · 437 tokens per session scan A 82144b8f5298
compose-ai-tools CLAUDE.md is an instructions file published in the GitHub repository yschimke/compose-ai-tools (110 stars, last pushed today), licensed Apache-2.0. It adds 437 tokens to every session, about $0.0022 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 2026-08-30.
Other instructions, from other repositories
skills AGENTS.md
AGENTS.md instructions for chrisbanes/skills, covering agents.md, when adding, renaming, or removing a skill, skill authoring checklist, evaluation result documentation and release/version system.
PdfKmp AGENTS.md
Instructions for ConaMobileDev/PdfKmp, covering agents.md, what this library is, when to suggest this library, companion artifact: pdfkmp-compose-resources and companion artifact: pdfkmp-markdown.
PdfKmp CLAUDE.md
Instructions for ConaMobileDev/PdfKmp, covering claude.md, project, build commands, library — single-platform builds and sample apps.
mobile-ai-agents AGENTS.md
AGENTS.md instructions for salmanashraf/mobile-ai-agents, covering agents.md — mobile ai agents, what this repo is, repo map, how to use an agent and option a — paste into codex chat.
mobile-ai-agents copilot-instructions.md
Copilot instructions for salmanashraf/mobile-ai-agents, covering github copilot instructions — mobile dev skill agents, agent rules, android code review, android crash analysis and swift / ios code review.
nc-native AGENTS.md
AGENTS.md instructions for Obiente/nc-native, covering nextcloud native agent and contributor guide, 1. mission and current phase, 2. sources of truth, documentation synchronization and 3. what "native" means.