What is brain-kit AGENTS.md?

Repository instructions for a learning kit in which an AI agent collects information from videos, articles, research papers, and code repositories and turns it into cited, reusable knowledge.

Use them to ingest a source, inspect relevant material, compare supporting evidence, summarize findings, and file knowledge for later use.

They provide a repeatable way to capture and check what was learned instead of letting useful information disappear after one session.

How 0xchamin/brain-kit configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to 0xchamin/brain-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/0xchamin/brain-kit/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/0xchamin/brain-kit

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/0xchamin/brain-kit/agents-md/github.svg)](https://agentmods.dev/instructions/0xchamin/brain-kit/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/0xchamin/brain-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/0xchamin/brain-kit/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/0xchamin/brain-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/0xchamin/brain-kit/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 9,708 This file is loaded in full into every session.

When invoked 9,708 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.09708	$0.09708
Opus 5.5	$0.03883	$0.03883
Sonnet 5.5	$0.01942	$0.01942
Haiku 4.5	$0.00971	$0.00971

Measured 2mo ago against content hash a7f46ce443b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

brain-kit 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 2mo 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.

AGENTS.md · 501 lines

How it starts

The opening of the file, as written. The whole thing — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Brain (agent-driven compounding learning kit)

Behavioral contract for any agent harness (Copilot CLI, Claude Code, Cursor, ...) working in this kit. Read this first, then the relevant sources/<id>/ and brain/. Brain turns things you learn from - YouTube videos, blog posts, research papers, and code repositories - into durable, cited, compounding knowledge.

The agent is the engine. There is no application. You (the agent) run the pipeline: capture the source, view visual candidates (your view tool is the vision model) or trace code (grep / code-intel tools), judge corroboration, distill, and file the knowledge. This is a kit for learning from sources - including repos - not for building on top of them. See prd.md for the full design.

Repo-specific defaults (this clone)

Default	Value	Used for
Owner	`chamin`	pre-fills the `SOURCE.md` Owner row (always this person)
Source naming	`YYMMDD_slug`	big-endian date sorts chronologically; `_` divides date/name, `-` between words (e.g. `260724_mcp-security-talk`)
Env	`.venv` in this folder	`yt-dlp`, `faster-whisper`, `imagehash`, `pillow` (see `requirements.txt`); `ffmpeg` is a system binary (macOS: `brew install ffmpeg`; Windows: `winget install Gyan.FFmpeg`); `git` for cloning code repos; `gh` (GitHub CLI) recommended for code sources (license, commit SHA, orient-before-clone) - optional
Seed topics	agents, mcp, skills, rag, agent-security, inferencing	live under `brain/topics/`; seeds, not a whitelist - the set is open (see "Scope: topics are open")
Repo clones	`sources/<id>/repo/` (git-ignored)	clone-per-source, snapshot pinned by commit SHA in `SOURCE.md`
Kit scripts	`tools/ingest.py` (mechanical toolbox), `validate.py` (contract type checker)	the only two frozen scripts; everything else is assembled per source

Scope: topics are open

The goal is to learn state-of-the-art AI broadly - agents, MCP, skills, RAG, agent-security, inferencing, and new topics as they emerge. The seed topics are a starting point, not a closed list. When a source teaches a recognizable, reusable area the brain does not yet cover, capture it as a new topic (see the compound step) - do not force it into an ill-fitting existing note. Domain guardrail: stay within AI / ML / agentic engineering; if a source is clearly off-domain, flag it and ask rather than silently ingesting. The architect persona owns the create-vs-merge call and keeps the taxonomy from ballooning.

Read the full file on GitHub · 501 lines

Changes

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.

2mo ago First seen · 501 lines · 9,708 tokens per session scan A a7f46ce443b8

Subscribe to this mod's changes

brain-kit AGENTS.md is an instructions file published in the GitHub repository 0xchamin/brain-kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 9,708 tokens to every session, about $0.0388 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 2026-08-31.

Learning and teaching Research

brain-kit AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
brain-kit AGENTS.md0xchamin/brain-kit	Instructions file	2	3mo ago	MIT	A	9,708	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

brain-kit: Instructions file for Codex