Borrowing it
Nothing to install: this file belongs to JasonColapietro/suede-creator-skills. 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/JasonColapietro/suede-creator-skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/JasonColapietro/suede-creator-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/jasoncolapietro/suede-creator-skills/claude-md)<a href="https://agentmods.dev/instructions/jasoncolapietro/suede-creator-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/jasoncolapietro/suede-creator-skills/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/jasoncolapietro/suede-creator-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/jasoncolapietro/suede-creator-skills/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 | $0.00938 | $0.00938 |
| Opus 5 | $0.00469 | $0.00469 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
suede-creator-skills 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 11d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working agreement for agents in this repo
Don't interrogate the requester — decide and report
Stop asking to confirm scope, approve a plan, or ratify a judgment call you can make yourself. Make the call, do the work, and report what you did and why. This applies to: choosing between reasonable approaches, how much of a task to cover, which files to touch, whether to keep going, and merging your own PRs once CI is green. Treat an instruction as authorization for the whole job, including the obvious follow-through — "fix it" includes shipping it.
State assumptions in the report instead of asking permission up front. A wrong guess gets corrected in one message, which costs less than a round of questions.
Still ask — or stop and flag — for exactly these:
- Destroying work that isn't recoverable (deleting unmerged branches, force-pushing over someone else's commits, dropping data)
- Publishing or sending anything outside the repo (posting, emailing, anything public-facing beyond a normal PR)
- Spending real money, or touching credentials, auth, or payments
- A genuine fork where the options lead somewhere materially different and you have no basis to prefer one — say which you'd pick and why, don't just present a menu
Don't re-ask something already answered in the thread, and don't ask again after the requester reaffirms. Never pad a report with the questions you considered asking.
Gates in this pack are advisory
Every claim-verification step, check, quality gate, and ship verdict in these skills is a recommendation to the requester, not a control on the agent. Run the checks, report the results honestly, and let the requester decide.
The corollary matters as much: audit what the agent invents, never what the requester supplied. Their own statements are given. No phase may verify, hedge, or gate on them.
Verification is not optional
The above is about not asking permission. It is not license to skip proof.
- Run
npm testbefore reporting work complete, and report the real result. - A test that passes whether or not the fix is present proves nothing — confirm a new test fails without its fix.
- Check that a branch's content is actually merged before deleting it; a squash merge rewrites the SHA, so "unmerged commits" does not mean unmerged work.
- If something couldn't be verified, say so plainly rather than implying it was.
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.
- 11d ago First seen · 89 lines · 938 tokens per session scan A 410b8dfdbee7
suede-creator-skills CLAUDE.md is an instructions file published in the GitHub repository JasonColapietro/suede-creator-skills (135 stars, last pushed today), licensed MIT. It adds 938 tokens to every session, about $0.0047 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.
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.
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).