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/0xchamin/brain-kit/agents-mdgit clone --depth 1 https://github.com/0xchamin/brain-kitWhat 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 | $0.09708 | $0.09708 |
| Opus 5 | $0.04854 | $0.04854 |
| Sonnet 5 | $0.01942 | $0.01942 |
| Haiku 4.5 | $0.00971 | $0.00971 |
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 yesterday.
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 — 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,
viewvisual candidates (yourviewtool 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. Seeprd.mdfor 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.
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.
- yesterday First seen · 501 lines · 9,708 tokens per session scan A a7f46ce443b8
brain-kit AGENTS.md is an instructions file published in the GitHub repository 0xchamin/brain-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 9,708 tokens to every session, about $0.0485 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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).
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.
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.