Borrowing it
Nothing to install: this file belongs to widnyana/eyay-toolkits. 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/widnyana/eyay-toolkits/main/CLAUDE.mdgit clone --depth 1 https://github.com/widnyana/eyay-toolkitsWrote 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/widnyana/eyay-toolkits/claude-md)<a href="https://agentmods.dev/instructions/widnyana/eyay-toolkits/claude-md"><img src="https://agentmods.dev/badge/instructions/widnyana/eyay-toolkits/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/widnyana/eyay-toolkits/claude-md"><img src="https://agentmods.dev/badge/instructions/widnyana/eyay-toolkits/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 | $0.00625 | $0.00625 |
| Opus 5.5 | $0.00250 | $0.00250 |
| Sonnet 5.5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
eyay-toolkits 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to agents working in this repository. Detailed rules live
in the per-directory AGENTS.md files — read the one for the tree you are touching.
Repository Overview
eyay-toolkits is a Claude Code plugin marketplace: a flat collection of independent,
self-contained plugins under plugins/, registered in .claude-plugin/marketplace.json.
Install via npx skills add widnyana/eyay-toolkits (skills.sh). There is no root build
system, package manager, or CI — each plugin/package is independent.
Where the details live
| Tree | Rules file | Covers |
|---|---|---|
plugins/ |
plugins/AGENTS.md |
Plugin anatomy, the plugin table, plugin tests, the add/modify checklist |
pi-packages/ |
pi-packages/AGENTS.md |
Dual-runtime (pi + omp) rules, version/omp checklists, shared-file drift sync |
Also: CONTRIBUTING.md (new plugin requirements), root README.md and INSTALL.md
(kept in sync by the per-dir checklists).
Global rules — MANDATORY
Local testing and validation before any push
Nothing ships to the remote without the user testing it locally first. The user decides when to push; agents NEVER push and NEVER ask to push. The session of 2026-09-03 shipped multiple unverified pushes — do not repeat that.
- Verify on the real surface before declaring done. A green test suite is not user-visible verification.
- Heavy automated tests are the baseline, not a substitute. Run the tests the per-dir rules file names; never report pass rates from memory.
- Claims must be verified or labeled. Untested behavior is
[INFERENCE]until someone runs it. When a claim is later falsified by a live test, correct the record immediately — including in docs and checklists that repeated it.
No over-engineering
If the solution becomes overly complex, the design is WRONG — stop and re-plan at the problem layer, not the implementation layer. Before adding machinery (subprocess chains, fallback trees, platform adapters), check whether the platform already solves the problem natively. When a simpler design exists, the complex one is a bug, not a v1.
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 · 55 lines · 625 tokens per session scan A 61ae10aca0bc
eyay-toolkits CLAUDE.md is an instructions file published in the GitHub repository widnyana/eyay-toolkits (8 stars, last pushed 2d ago), licensed MIT. It adds 625 tokens to every session, about $0.0025 per session on Opus 5.5. 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 2026-10-17.
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.