Borrowing it
Nothing to install: this file belongs to yammaku/cross-agent-skills-template. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yammaku/cross-agent-skills-template/main/CLAUDE.mdgit clone --depth 1 https://github.com/yammaku/cross-agent-skills-templateWrote 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/yammaku/cross-agent-skills-template/claude-md)<a href="https://agentmods.dev/instructions/yammaku/cross-agent-skills-template/claude-md"><img src="https://agentmods.dev/badge/instructions/yammaku/cross-agent-skills-template/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/yammaku/cross-agent-skills-template/claude-md"><img src="https://agentmods.dev/badge/instructions/yammaku/cross-agent-skills-template/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00975 | $0.00975 |
| Opus 5 | $0.00487 | $0.00487 |
| Sonnet 5 | $0.00195 | $0.00195 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
cross-agent-skills-template 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 10d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file mirrors the repo-local development intent of AGENTS.md for harnesses that recognize CLAUDE.md.
Use it when the active project is this skills-registry repo and the user wants to improve the system.
Read Order
What This Repo Is
This template is the source-of-truth catalog and install-management system for agent skills across Antigravity, Claude Code, Codex, and Gemini CLI.
It contains:
- canonical skill sources under
skills/ - adapter files under
agents/ - agent-global manifests under
manifests/agent-global/ - generated install views under
installs/agent-global/ - bootstrap and migration tooling for onboarding a new machine
This repo is the public minimal template, not the user's lived-in private registry. Its private sibling currently lives at agent-skills.
Key Rules
- All agents follow the same repo-first lifecycle: create or import into the repo, classify, install through manifests, sync, and validate.
sharedis a source category, not an install policy.agents/<agent>.tomlis the compatibility layer for each harness's native paths.agents/<agent>.tomlalso defines the agent-global install materialization strategy.- Agent-global installs are per-agent and live in
manifests/agent-global/<agent>.toml. - Generated install views are outputs, not primary authoring surfaces.
- Antigravity does not get a separate lifecycle. It adds one compatibility layer because its native global scanner needs real top-level skill directories.
- README is the AI-led onboarding contract for fresh install and migration.
- Project installs are shared-only. They live in a project's
.agent-skills.tomland materialize into.agents/skillsplus native mirrors such as.codex/skillsand.claude/skillsfor host-specific discovery. - Treat
.agents/skillsas the preferred interoperable Agent Skills surface. Native mirrors such as.codex/skillsand.claude/skillsare compatibility projections of the same shared install set, not separate ownership domains or separate standards. - In managed projects,
.agent-skills.tomlshould stay tracked, while generated project surfaces, the managed state file, and project skill backups should be gitignored. - When project skill discovery differs across harnesses, assume the problem is materialization shape before assuming the system needs another authoring surface.
- Onboarding migration stays agent-global only. Explicit post-bootstrap project-local adoption belongs in
manage_agent_skills.py adopt-project. - On an already managed machine, resolve repo git state before running
sync-agent-globalorsync-project. - Treat project-level validation as first-class too.
checkonly covers the catalog and agent-global install views; usecheck-project --project <path>when changing project install behavior or debugging project mirrors. - Do not hard-code the repo path.
- Do not shadow a shared skill with the same name in an agent folder.
- If a shared skill needs divergence, create a renamed agent-specific variant.
- Keep the template minimal and productized. Do not copy private catalog history or private manifest clutter into it.
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.
- 10d ago First seen · 75 lines · 975 tokens per session scan A 6dc447b12744
cross-agent-skills-template CLAUDE.md is an instructions file published in the GitHub repository yammaku/cross-agent-skills-template (11 stars, last pushed 5mo ago), licensed MIT. It adds 975 tokens to every session, about $0.0049 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.