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/alex-feel/claude-code-artifacts-public/claude-mdgit clone --depth 1 https://github.com/alex-feel/claude-code-artifacts-publicWrote 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/alex-feel/claude-code-artifacts-public/claude-md)<a href="https://agentmods.dev/instructions/alex-feel/claude-code-artifacts-public/claude-md"><img src="https://agentmods.dev/badge/instructions/alex-feel/claude-code-artifacts-public/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 | $0.00835 | $0.00835 |
| Opus 5 | $0.00417 | $0.00417 |
| Sonnet 5 | $0.00167 | $0.00167 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
claude-code-artifacts-public 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 5d 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 — 39 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 repository.
This repository is a public library of reusable Claude Code artifacts. Each artifact type lives under its own <type>/library/ directory (skills/library/, hooks/library/, rules/library/, agents/library/, slash-commands/library/) or, for environments, under environments/library/ and environments/templates/. Every type also carries a short README describing its own layout, conventions, and installation.
README maintenance
The root README.md is a catalog organized by artifact category, not a description of the directory tree. It deliberately has no "repository structure" section: a reader should meet the actual, useful artifacts first, then learn how to consume them.
Category order
Present categories in this fixed order, skipping any that are currently empty:
- Environments
- Skills
- Rules
- Hooks
- Agents
- Slash commands
The order is fixed even as categories come and go; when a category gains its first artifact it takes its slot in this sequence, and the categories that remain are shown in this same relative order.
A category appears only when it has content
A category earns its own ## section in the root README only when the repository actually contains at least one standalone artifact of that type under the type's library/ directory. A type whose library/ holds no standalone artifacts yet — only its own README.md or files that serve another artifact — is omitted from the root catalog until its first standalone artifact lands. The goal is that every section a reader sees points at something real they can use, never at an empty placeholder.
Only standalone artifacts are cataloged
The catalog describes only standalone entities: artifacts that deliver value installed on their own. The repository holds many files, and not every file warrants a description. A file that works only as part of a larger artifact — a shared helper module several hooks load, a hook's companion configuration, or an environment configuration's bundled skill, hooks, and runtime files — never gets its own ### subsection: it is described (and linked) inside the entry of the artifact it serves, or, for a cross-cutting helper, mentioned in its category's prose. The test is whether a reader could install the file alone and get value from it; if it only makes sense wired into something larger, it belongs inside that larger artifact's entry.
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.
- 5d ago First seen · 39 lines · 835 tokens per session scan A a5df1fc7e2ca
claude-code-artifacts-public CLAUDE.md is an instructions file published in the GitHub repository alex-feel/claude-code-artifacts-public (6 stars, last pushed 10d ago), licensed MIT. It adds 835 tokens to every session, about $0.0042 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
cconami CLAUDE.md
Claude Code instructions for memyselfandm/cconami, covering claude code enhancements system, project overview, project goals, architecture overview and core components.
claude-code-toolbox CLAUDE.md
Instructions for alex-feel/claude-code-toolbox, covering claude.md, repository purpose, key architecture, two-tier installation system and native claude code installation support.
claude-skills CLAUDE.md
Claude Code instructions for secondsky/claude-skills, covering claude skills - project context, ⚠️ critical: communication rule — the most important rule, ⚠️ critical: repository policy - never touch jezweb repo, ❌ forbidden actions (jezweb repo) and ✅ required actions (secondsky repo).
headsup CLAUDE.md
Claude Code instructions for wasulajr/headsup, covering releases are mandatory (issue #19), bootstrap files and authoring skills (skill.md frontmatter).
claude_extensions CLAUDE.md
Instructions for kimon1230/claude_extensions, covering global claude.md, persona, hard rules, code quality and planning.
goblin-mode CLAUDE.md
Claude Code instructions for JasonWarrenUK/goblin-mode, covering jason warren - claude code config, 1. technical profile, 1a. scales: preference & proficiency, 1b. domains and 1.2. frontend.