Borrowing it
Nothing to install: this file belongs to GeekyAnts/geeklego. 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/GeekyAnts/geeklego/geeklego-v2-beta/AGENTS.mdgit clone --depth 1 https://github.com/GeekyAnts/geeklegoWrote 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/geekyants/geeklego/agents-md)<a href="https://agentmods.dev/instructions/geekyants/geeklego/agents-md"><img src="https://agentmods.dev/badge/instructions/geekyants/geeklego/agents-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/geekyants/geeklego/agents-md"><img src="https://agentmods.dev/badge/instructions/geekyants/geeklego/agents-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 | $0.01876 | $0.01876 |
| Opus 5 | $0.00938 | $0.00938 |
| Sonnet 5 | $0.00375 | $0.00375 |
| Haiku 4.5 | $0.00188 | $0.00188 |
Grade A, and why
geeklego AGENTS.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 9d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — GeekLego (v2)
First Things
Read CLAUDE.md — it's the single source of truth for the v2 system: the 2-tier
token model (primitives → standard ShadCN/Tailwind semantics), the ShadCN/Radix component
pattern, the file layout, and all the "never" / "always" rules. The reference implementation
is the Button slice at components/v2/Button/ — read it before
building anything. AGENTS.md only adds operational detail that CLAUDE.md omits; where the
two ever disagree, CLAUDE.md wins.
Package manager is pnpm.
npm installis hard-blocked by apreinstall: only-allow pnpmguard (npm's installer crashes on this pnpm-built tree). Install deps withpnpm add <pkg>— nevernpm install. Running scripts works under either runner (pnpm run …≡npm run …).
Commands
pnpm run dev:all # Token editor cockpit + Storybook side-by-side
pnpm run dev # Token editor only (Vite, --config vite.config.mts, serves app/)
pnpm run storybook # Storybook only (port 6006, .storybook/main.ts globs components/v2/**)
pnpm run build # tsup bundle (components/index.ts, esm+cjs+dts) + build:css
pnpm run build:css # Compile design-system/v2/index.css → dist/geeklego.css
pnpm run build-storybook # Static Storybook site (passes — legacy stories/** are not globbed)
pnpm run lint # ESLint, --max-warnings 0 (also enforces v2 import discipline)
pnpm run lint-css # Stylelint over design-system/v2/**
pnpm run validate-tokens # 2-tier chain check (primitive → semantic); must exit 0
pnpm run export-ir # Export token IR
pnpm run export-design-md # Export design.md
npx tsc --noEmit # Type-check
npx vitest run # All tests (app/src/**/*.test.ts + scripts/**/*.test.ts)
There is no test script — run Vitest directly (npx vitest run).
Repo Structure
vite.config.mts— app dev server + a live inline plugin that reads/writesdesign-system/v2/anddesign-system/tokens.metadata.json(the cockpit's token-CRUD and/api/merge-metadataendpoints). There is no standalone token-api server.vitest.config.ts— single test project:app/src/**/*.test.ts+scripts/**/*.test.ts. (No separate Storybook/Playwright test project.)eslint.config.mjs— flat config. Enforces v2 import discipline viano-restricted-imports: bans**/{atoms,molecules,organisms}/**and directdesign-system/geeklego.cssimports. Baseline is 0 warnings under--max-warnings 0; any new warning fails the gate..stylelintrc.mjs— stylelint config (scoped todesign-system/v2/**).tsup— no config file; library build uses tsup defaults for thecomponents/index.tsentry.design-system/v2/is the only live stylesheet tree;design-system/geeklego.csswas deleted in the 2-tier cut.design-system/v2-defaults/holds the factory-reset baseline.
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.
- 9d ago First seen · 112 lines · 1,876 tokens per session scan A d21154fa096b
geeklego AGENTS.md is an instructions file published in the GitHub repository GeekyAnts/geeklego (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,876 tokens to every session, about $0.0094 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
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.