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/lovstudio/skills/claude-mdgit clone --depth 1 https://github.com/lovstudio/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/lovstudio/skills/claude-md)<a href="https://agentmods.dev/instructions/lovstudio/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/lovstudio/skills/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 | $0.01821 | $0.01821 |
| Opus 5 | $0.00911 | $0.00911 |
| Sonnet 5 | $0.00364 | $0.00364 |
| Haiku 4.5 | $0.00182 | $0.00182 |
Grade A, and why
skills CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 官网 revalidate 的 secret 环境变量名是 `LOVSTUDIO_REVALIDATE_SECRET`（publisher 文档里的 `SKILL_REVALIDATE_SECRET` 已过时），curl 用 `x-revalidate-secret` header 直接读该变量（2026-08-20, 18bc301） How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working in this repo.
What This Is
The central index for Lovstudio skills. The source of truth for each skill is its own repo at github.com/lovstudio/{name}-skill. Locally, skills are developed under ~/lovstudio/coding/skills/{name}-skill/.
This index repo also carries a read-only mirror of every free skill under ./skills/<name>/ and encrypted distribution bundles for paid skills. The mirror exists so that the npx skills add lovstudio/skills discovery flow (used internally by the lovstudio CLI) can find every skill in a single clone — that flow only resolves local paths in .claude-plugin/marketplace.json, not external github sources.
Repo Layout
.
├── README.md / README.en.md # Human-readable catalog (CI-rendered between SKILLS:START/END)
├── skills.yaml # Machine-readable manifest — SOURCE OF TRUTH
├── skills/<name>/ # Free mirrors or encrypted paid bundles (generated distribution content)
├── .claude-plugin/marketplace.json # Claude Code marketplace manifest (auto-rendered)
├── scripts/sync-skills.py # Mirrors each free repo into ./skills/<name>/ (shallow clone + rsync)
├── scripts/sync-runtime-names.py # Syncs runtime_name from mirrored SKILL.md frontmatter
├── scripts/render-marketplace.py # Regenerates marketplace.json from skills.yaml
├── scripts/render-readme.py # Regenerates README skill table from skills.yaml
├── CHANGELOG.md # Index repo history (not per-skill)
├── LICENSE # MIT (for this index; each skill has its own LICENSE)
└── .github/workflows/ # render-readme.yml runs sync → render-marketplace → render-readme
Edit skills.yaml, not the README table or marketplace.json. Free mirrors and paid bundles under skills/ are distribution outputs. CI regenerates the catalog and free mirrors on push and nightly. You can preview locally with python3 scripts/sync-skills.py && python3 scripts/render-marketplace.py && python3 scripts/render-readme.py.
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 · 106 lines · 1,821 tokens per session scan A 07e89de189ca
skills CLAUDE.md is an instructions file published in the GitHub repository lovstudio/skills (64 stars, last pushed yesterday), licensed MIT. It adds 1,821 tokens to every session, about $0.0091 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
cli-continues CLAUDE.md
Instructions for yigitkonur/cli-continues, covering claude.md, what this project is, build & development commands, architecture and core flow.
cli-continues parsers.instructions.md
Instructions for yigitkonur/cli-continues, covering parser review guidelines, crash safety (critical), required exports, jsonl streaming and tool summarizer.
cli-continues ci.instructions.md
Instructions for yigitkonur/cli-continues, covering ci workflow review guidelines, security, prefer explicit permissions scoping, node.js version requirements and package manager.
cli-continues security.instructions.md
Instructions for yigitkonur/cli-continues, covering security review guidelines — core utilities, command injection prevention (resume.ts), forward flag security (forward-flags.ts), handoff output safety (markdown.ts) and general.
cli-continues typescript.instructions.md
Instructions for yigitkonur/cli-continues, covering typescript review guidelines, type safety, discriminated unions, async patterns and import rules.
AgentHarbor CLAUDE.md
Instructions for abhiunix/AgentHarbor, covering claude.md, commands, architecture, two tauri windows and adapter trait — the core abstraction.