Borrowing it
Nothing to install: this file belongs to Neeeophytee/finding-unknowns-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/Neeeophytee/finding-unknowns-skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-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/neeeophytee/finding-unknowns-skills/claude-md)<a href="https://agentmods.dev/instructions/neeeophytee/finding-unknowns-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/neeeophytee/finding-unknowns-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/neeeophytee/finding-unknowns-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/neeeophytee/finding-unknowns-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 | $0.01447 | $0.01447 |
| Opus 5.5 | $0.00579 | $0.00579 |
| Sonnet 5.5 | $0.00289 | $0.00289 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
finding-unknowns-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 1mo 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.
This is a copy
100% identical to finding-unknowns-skills AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo notes
This repo ships agent skills distilled from two Thariq Shihipar essays. It is a Claude Code plugin, a Codex plugin, its own single-plugin marketplace on both, and a plain SKILL.md collection installable into Kimi, Cursor, and Hermes. Everything below is a gotcha about maintaining it — none of it ships to users.
What ships, and the gate that decides
.claude-plugin/plugin.json's skills array is the ship gate for the Claude Code plugin. A skill directory that exists under skills/ but is missing from that array does not reach Claude Code plugin users, even though npx skills add, manual cp -r, the Codex plugin, and Hermes will still pick it up. (The Codex manifest uses "skills": "./skills/" — the whole directory — so it has no per-skill gate; the Claude array is the only explicit gate. Keep the array complete anyway; it's the intended control.) Add every new skill to the array in the same commit that creates it.
Version lives in THREE manifests — move them together
version is what tells already-installed users an update exists. It is duplicated and must stay in lockstep:
.claude-plugin/plugin.json.codex-plugin/plugin.json- (a root
plugin.jsontoo, if Antigravity support ever lands — seeFUTURE-EXTENSIONS.md)
marketplace.json and .agents/plugins/marketplace.json carry no version field. A version mismatch ships silently — no error, just wrong "update available" signals. Also tag the release (git tag -a vX.Y.Z) and gh release create; bumping the manifest alone does not create a GitHub release.
Never add Co-Authored-By / AI-attribution trailers to commits, PRs, or releases — it registers a bot on the contributor list.
Files that must be edited together
CLAUDE.mdandAGENTS.mdare byte-identical. Edit both, ordifffails.- The skill count is hardcoded in
README.md(4 places) and inplugin.json'sdescription, which also enumerates every skill by name. - Two of those README lines are verification claims, not prose. Find-and-replacing the number in them turns a verified claim into an unverified one. Re-run both and edit to what you observed:
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.
- 1mo ago First seen · 74 lines · 1,447 tokens per session scan A d711ca83d0cc
finding-unknowns-skills CLAUDE.md is an instructions file published in the GitHub repository Neeeophytee/finding-unknowns-skills (356 stars, last pushed 1mo ago), licensed MIT. It adds 1,447 tokens to every session, about $0.0058 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to finding-unknowns-skills AGENTS.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.