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/voidmatcha/ui-clone-skills/agents-mdgit clone --depth 1 https://github.com/voidmatcha/ui-clone-skillsWhat 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 | $0.02439 | $0.02439 |
| Opus 5 | $0.01220 | $0.01220 |
| Sonnet 5 | $0.00488 | $0.00488 |
| Haiku 4.5 | $0.00244 | $0.00244 |
Grade A, and why
ui-clone-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 3d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — ui-clone-skills development guide
ui-clone-skills is motion forensics for the animated web — four jobs against a live URL (decode / clone / verify / extract) backed by one extraction engine that pulls real CSS + animation params from JS bundles and verifies with AE/SSIM diff.
Canonical project guide for Claude Code, Codex, and other agent hosts. Claude Code loads CLAUDE.md, which imports this file via @AGENTS.md; Codex and other AGENTS.md-aware tools read this file directly.
Project structure
ui_clone/ Python package (gates, hooks, pipeline, DAG, metrics)
skills/ 3 reusable skills; skill-owned primitives live under skills/<skill>/scripts/
scripts/ Repo automation: ci/, hooks/, extract/, verify/
hooks/ Claude/Codex host hook registration and shim plumbing
tests/ pytest suite for gates, hooks, metrics, and pipeline behavior
.claude-plugin/ Claude Code plugin manifest and marketplace metadata
.codex-plugin/ Codex plugin manifest
CLAUDE.md Thin Claude Code entrypoint that imports this file
Script location policy
- Host lifecycle hook registration stays in
hooks/(hooks.json,codex-hooks.json,shim.sh). Do not moveshim.shintoscripts/; hook manifests call it as host integration plumbing. - Repo-level automation lives in
scripts/:scripts/ci/for CI/review/security,scripts/hooks/for local git/tool hooks,scripts/extract/for shared extraction helpers, andscripts/verify/for shared verification wrappers. - Skill-owned primitives live under
skills/<skill>/scripts/.skills/visual-debug/scripts/owns AE/SSIM, section, transition, and visual-diff primitives. - Orchestration skills should reference shared/skill-owned scripts by their canonical location instead of duplicating compatibility shims.
Verification gate (must pass before commit)
[] bash scripts/ci/ci-local.sh — 0 failures (mirrors GitHub Actions test job; runs pytest + mypy + ruff + shell + review)
[] bash scripts/ci/pre-push-security.sh — 0 blockers (security + cross-ref + version sync)
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.
- 3d ago First seen · 106 lines · 2,439 tokens per session scan A 486e1100a4e4
ui-clone-skills AGENTS.md is an instructions file published in the GitHub repository voidmatcha/ui-clone-skills (8 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,439 tokens to every session, about $0.0122 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
claude-code-karma CLAUDE.md
Instructions for JayantDevkar/claude-code-karma, covering claude.md, project overview, quick start, clone (no submodule init needed — this is a monorepo) and start api (terminal 1).
claude-code-skills CLAUDE.md
Instructions for levnikolaevich/claude-code-skills, a project described as: Standalone engineering skills for Claude Code and Codex: review, audit, optimization, testing, product discovery, architecture, and safe publishing.
claude-code-eyes CLAUDE.md
Instructions for fcavalcantirj/claude-code-eyes, covering claude-code-eyes — notes for claude code, what it is, load-bearing invariants (do not "simplify" these away), frontmatter rules (enforced by the skill-creator validator) and how to test (everything must pass under bash 3.2).
opinionated-claude-skills CLAUDE.md
Claude Code instructions for Pyroxin/opinionated-claude-skills, covering claude.md, critical requirement, repository structure, pre-publication validation and build system.
autorun CLAUDE.md
Claude Code instructions for ahundt/autorun, a project described as: Claude Code & codex plugin + Gemini cli extension to keep ai running, keep data safe, plan better, and keep running until tasks are done.
ralvaskills CLAUDE.md
Claude Code instructions for ralvarezdev/ralvaskills, a project described as: My personal, ever-growing collection of AI skills for OpenCode and Claude Code. Enforces strict clean architecture and professional standards.