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/lienjack/learn-agent/agents-mdgit clone --depth 1 https://github.com/LienJack/learn-agentWhat 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 | $0.00882 | $0.00882 |
| Opus 5 | $0.00441 | $0.00441 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
learn-agent 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 2d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This repository is an Astro-based content site. Application code lives in src/: pages in src/pages/, shared layouts in src/layouts/, UI components in src/components/, styles in src/styles/, and site constants in src/consts.ts. Blog content is stored in src/content/blog/ and validated through src/content.config.ts. Static assets that should be served directly belong in public/; bundled images and fonts belong in src/assets/. Planning and design notes live in docs/.
Build, Test, and Development Commands
- This project uses
pnpmas the default package manager. Preferpnpmcommands and keeppnpm-lock.yamlauthoritative; do not updatepackage-lock.jsonfor normal dependency changes. pnpm install— install dependencies; use Node.js>=22.12.0as defined inpackage.json.pnpm dev— start the local Astro dev server athttp://localhost:4321.pnpm build— generate the production site intodist/.pnpm preview— serve the built output locally for a final check.pnpm astro check— run Astro’s project checks when validating routes, content, and types.
Coding Style & Naming Conventions
Follow the existing style: TypeScript, Astro, and CSS use tabs for indentation. Name Astro components in PascalCase, for example BaseHead.astro; React components also use PascalCase and live in focused folders such as src/components/home/HomePage.tsx. Keep constants in uppercase snake case when exported globally, such as SITE_TITLE. Use kebab-case for content filenames like welcome.md. Prefer small, composable components and keep copy or content-specific data close to the page or component that uses it.
Testing Guidelines
There is no dedicated test suite yet. Before opening a PR, run pnpm build and pnpm astro check to catch content schema, routing, and type issues. When adding tests in the future, place them near the feature they cover or under a clear tests/ directory, and use names that mirror the target module.
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.
- 2d ago First seen · 43 lines · 882 tokens per session scan A c9c60d0e9855
learn-agent AGENTS.md is an instructions file published in the GitHub repository LienJack/learn-agent (23 stars, last pushed 1mo ago), licensed MIT. It adds 882 tokens to every session, about $0.0044 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
llm-wiki-agent GEMINI.md
Instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
DocMason copilot-instructions.md
Instructions for JetXu-LLM/DocMason, covering docmason github copilot notes and copilot-specific delta.
DeepRefine-Skill GEMINI.md
Instructions for HKUST-KnowComp/DeepRefine-Skill, covering deeprefine skill for gemini cli, core behavior and commands.
student-llm-wiki AGENTS.md
Instructions for IssacW228/student-llm-wiki, covering student llm wiki — agent instructions, 操作规则 operation rules, token预算规则（最高优先级）, 架构 architecture and 命令 commands.
ScalaSemantic AGENTS.md
Instructions for MercurieVV/ScalaSemantic, covering agents.md instructions and quick start.
aptu-coder AGENTS.md
AGENTS.md instructions for clouatre-labs/aptu-coder, covering agents.md, project structure, ci runners, commands and observability.