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/treattrick/skill-sync/claude-mdgit clone --depth 1 https://github.com/TreatTrick/skill-syncWrote 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/treattrick/skill-sync/claude-md)<a href="https://agentmods.dev/instructions/treattrick/skill-sync/claude-md"><img src="https://agentmods.dev/badge/instructions/treattrick/skill-sync/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 | $0.00425 | $0.00425 |
| Opus 5 | $0.00212 | $0.00212 |
| Sonnet 5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
skill-sync 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 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.
What it actually says
CLAUDE.md
Follow the same engineering rules defined in AGENTS.md. Key reminders:
- Preserve existing comments. If new comments are necessary, write them in Chinese.
- Use
apply_patchfor manual file edits. - Organize Svelte code under
src/routes,src/app,src/shared, andsrc/modules. - Do not add wrappers that only forward runes state reads or setter calls.
- Put user-facing Chinese copy in
src/shared/i18n/localesand read it witht(...). - Use only semantic color tokens exposed by
src/index.css. - Do not use arbitrary Tailwind text sizes, arbitrary radius classes, or large arbitrary sizing classes without responsive or local-overflow guardrails.
- Keep imports flowing
routes -> app -> modules -> shared; do not create circular imports, self imports, orexport *barrels. - Let Prettier own formatting; use
npm run formator rely onlint-staged, and check withnpm run format:checkbefore larger handoffs. - After UI or layout changes, run
npm run lint:responsive,npm run lint:colors, andnpm run lint:i18nas appropriate. Before completion, runnpm run lintandnpm run build. - Prefer shadcn-svelte components from
src/shared/uifor UI; add new ones withnpx shadcn-svelte@latest add <name>. Hand-build only when no shadcn equivalent exists (Spinner, EmptyState, StatusBadge).
AI Collaboration Rules
- Prefer directly completing the user's request. Ask only when key information is missing and a safe assumption is not possible.
- Do not overwrite or revert user changes.
- If the user explicitly says not to write tests, do not add tests.
- Do not report completion based on assumptions. Report actual verification command output.
- Do not move module-private code into
sharedunless the concept is stable, clearly named, and reused.
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 · 24 lines · 425 tokens per session scan A f0774256cc83
skill-sync CLAUDE.md is an instructions file published in the GitHub repository TreatTrick/skill-sync (4 stars, last pushed 14d ago), licensed MIT. It adds 425 tokens to every session, about $0.0021 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
Khaos-Brain AGENTS.md
Instructions for liuyingxuvka/Khaos-Brain, covering repository expectations, bootstrap, start here, purpose and github publish default.
Copilot-Skills svelte.instructions.md
Instructions for TheSethRose/Copilot-Skills, covering svelte instructions, default behaviors, common workflows, setup & installation and development.
Copilot-Skills sveltekit.instructions.md
Instructions for TheSethRose/Copilot-Skills, covering sveltekit instructions, default behaviors, common workflows, setup & installation and development.
Copilot-Skills vue.instructions.md
Instructions for TheSethRose/Copilot-Skills, covering vue instructions, default behaviors, common workflows, setup & installation and development.
mulmoterminal CLAUDE.md
Claude Code instructions for receptron/mulmoterminal, covering claude.md — mulmoterminal, stack & package manager, run after changes, import a component at module scope, never inside a test and no emojis.
moonproxy-desktop AGENTS.md
AGENTS.md instructions for MoonProxyHQ/moonproxy-desktop, covering moonproxy, 功能, 技术栈, 目录结构 and 配置与数据存储.