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/joyehuang/minimind-notes/agents-mdgit clone --depth 1 https://github.com/joyehuang/minimind-notesWrote 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/joyehuang/minimind-notes/agents-md)<a href="https://agentmods.dev/instructions/joyehuang/minimind-notes/agents-md"><img src="https://agentmods.dev/badge/instructions/joyehuang/minimind-notes/agents-md.svg" alt="Measured on agentmods" 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 | $0.00597 | $0.00597 |
| Opus 5 | $0.00298 | $0.00298 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
minimind-notes 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 3d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
modules/holds the teaching modules (e.g.,modules/01-foundation/01-normalization/withteaching.md,code_guide.md,quiz.md, andexperiments/).docs/,index.md, anden/contain VitePress content; site config lives in.vitepress/.learning_materials/stores runnable example scripts;docs/and top-levellearning_log.md/knowledge_base.mdstore notes.model/,trainer/, anddataset/mirror the MiniMind code, training scripts, and datasets used by experiments.public/andimages/host static assets used by the docs site.
Build, Test, and Development Commands
- Use
pnpmfor package management in this repo. pnpm installinstalls VitePress dependencies.pnpm run docs:devstarts the local VitePress dev server.pnpm run docs:buildbuilds the static site to.vitepress/dist.pnpm run docs:previewserves the built site for verification.python modules/01-foundation/01-normalization/experiments/exp1_gradient_vanishing.pyruns a sample experiment.pip install -r requirements.txtinstalls Python dependencies for experiments and training scripts.
Coding Style & Naming Conventions
- Python follows PEP 8;
blackis acceptable for formatting when needed. - Experiments should be self-contained, use fixed seeds, and include clear (often Chinese) comments.
- Experiment filenames use
exp{N}_{description}.pyand store expected outputs inresults/. - Module folders use
NN-topic-namenumbering for ordering (e.g.,01-normalization). - Markdown should use clear headings and short, instructional paragraphs.
Testing Guidelines
- There is no formal test runner; validate changes by building docs and running relevant experiments.
- Keep experiment outputs reproducible and commit expected results under the module
results/folder.
Commit & Pull Request Guidelines
- Use Conventional Commit-style messages:
feat:,fix:,docs:,refactor:,perf:,style:,test:,chore:,experiment:with optional scopes (e.g.,fix(build): ...). - Keep PRs small and focused on a single feature or fix.
- Use
.github/PULL_REQUEST_TEMPLATE.mdand link related issues (e.g.,Closes #123). - Update relevant docs when behavior or experiments change, and ensure new experiments run independently.
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.
- 3d ago First seen · 38 lines · 597 tokens per session scan A e15311e909f7
minimind-notes AGENTS.md is an instructions file published in the GitHub repository joyehuang/minimind-notes (177 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 597 tokens to every session, about $0.0030 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
transformers copilot-instructions.md
Instructions for huggingface/transformers, covering copilot-instructions.md guide for hugging face transformers, core project structure, coding conventions for hugging face transformers, copying and inheritance and testing.
DeepSpeed AGENTS.md
AGENTS.md instructions for deepspeedai/DeepSpeed, covering deepspeed project rules, commit & ci requirements, code change discipline, tool caveats and edit tool auto-formatter.
streamlit copilot-instructions.md
Copilot instructions for streamlit/streamlit, covering streamlit repo overview, tech stack, folder structure, shell & build policy and make commands.
pytorch CLAUDE.md
Claude Code instructions for pytorch/pytorch, covering ai policy — mandatory, scratch space, pr review, environment and ci docker images.
pytorch copilot-instructions.md
Copilot instructions for pytorch/pytorch, covering pytorch copilot instructions, architecture overview, core components, the code generation workflow and development workflows.
pytorch AGENTS.md
AGENTS.md instructions for pytorch/pytorch, a project described as: Tensors and Dynamic neural networks in Python with strong GPU acceleration.