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/camilleroux/genart-skill/agents-mdgit clone --depth 1 https://github.com/camilleroux/genart-skillWrote 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/camilleroux/genart-skill/agents-md)<a href="https://agentmods.dev/instructions/camilleroux/genart-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/camilleroux/genart-skill/agents-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 | $0.00763 | $0.00763 |
| Opus 5 | $0.00381 | $0.00381 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade C, and why
genart-skill AGENTS.md scanned grade C 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 today.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/pc && cp -r scripts /tmp/pc # the plugin-cache layout: How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on this repo
This repo IS a Claude Code plugin. Plugin users get skills/genart/SKILL.md
through the plugin system — this file is only for sessions editing the repo.
Editorial rules (the ones a fresh session breaks in good faith)
- Platform sheets are pointers, not copies. No library versions, no numeric
values, no API field names in
references/platforms/*.md— only the stable mental model, the doc URLs, and questions to ask those docs. Copied values go stale and are then worse than absent. Resist "just this one value".artpoint.mdis the documented exception: Artpoint publishes no artist specification, so there is nothing to point at. Its delivery table carries real values with a provenance stamp and a date — keep both, and do not copy the pattern to a sheet whose platform has public docs. - fxhash is never mentioned (platform offline). Its concepts (mint-time
params, preview trigger) are described neutrally in
self-hosted.md. - Every reference sheet starts with
<!-- Verified: YYYY-MM-DD -->— update it when you actually re-verify, not when you merely edit. - Concise: lists, tables, code — one sentence per idea. Platform sheets ~30–50 lines, transverse sheets ~50–120. No narrative prose.
- Tone: defaults with legitimate counter-examples, never absolute rules.
ethics.mdis the only normative sheet. - All content in English.
Architecture invariants
- Zero dependencies in the plugin. No package.json. Playwright lives in the artist's project; scripts print the install command when it is missing.
- Scripts run in place via
$CLAUDE_PLUGIN_ROOT, never copied into projects. scripts/lib.mjsholds the shared contract encoding (launch flags, "render is done" wait, server).check.mjsandrender.mjsmust both use it — duplicating any of it lets the checker and renderer silently diverge.tests/fixture/is the sketch contract incarnate (defined inreferences/platforms/self-hosted.md). The broken variant is derived by sed in CI, never stored — see.github/workflows/ci.yml.- The version lives in
.claude-plugin/plugin.jsononly. A release = bump it there + add aCHANGELOG.mdentry (the update-communication channel).
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.
- today Changed · +6 lines · +109 tokens per session scan A → C 0cce8f8cc069
- 6d ago First seen · 50 lines · 654 tokens per session scan A af65517a625c
genart-skill AGENTS.md is an instructions file published in the GitHub repository camilleroux/genart-skill (136 stars, last pushed today), licensed MIT. It adds 763 tokens to every session, about $0.0038 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
TDPilot AGENTS.md
Instructions for dreamrec/TDPilot, covering tdpilot agent guide, default workflow, touchdesigner safety and verification.
Paperlab AGENTS.md
AGENTS.md instructions for NourMtir0722/Paperlab, covering paperlab — for coding agents, integrating paperlab into a project, stage mode — paper as architecture, content types and lighting is data, not an enum.
Looptimal CLAUDE.md
Instructions for Renn-Labs/Looptimal, covering looptimal — repo guidance for ai agents, build journal — capture the concepts, not the changelog and — .
ai-software-architect AGENTS.md
AGENTS.md instructions for codenamev/ai-software-architect, covering agents.md - ai software architect framework, project overview, framework development setup, repository structure and installation for framework development.
embedded-systems-architect AGENTS.md
Instructions for Zachariah9420/embedded-systems-architect: This repository ships an agent skill for embedded-systems and edge-AI development work.
superpowers-graph CLAUDE.md
Claude Code instructions for RonMizrahi/superpowers-graph, covering superpowers-graph — repository guide, sources of truth, changing the graph — the eval ships with the change and rules that are not obvious from the code.