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/aliafshar/brain/gemini-mdgit clone --depth 1 https://github.com/aliafshar/brainWhat 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 | $0.01188 | $0.01188 |
| Opus 5 | $0.00594 | $0.00594 |
| Sonnet 5 | $0.00238 | $0.00238 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
brain GEMINI.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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent Framework
The basic concept will be a "Goal" that will be analyzed and reported on in a "run". Each "run" will have its own working directory in runs subdirectory.
Core Concepts
- Goal: A statement or question that will need to be analyzed and reported on.
- WorkItem: A task to be completed by an agent. It has a
descriptionand aresult. - Run: Manages the state for a given
Goal. It tracks allWorkItems and other necessary state. - Agent Persona: A definition of an agent's capabilities, expertise, and personality, stored as a heading in the
agents.mdfile.
Run Directory & Artifacts
Each run will have a unique directory inside the runs directory. The directory name will be prefixed with a timestamp in the format YYYYMMDD_hhmmss_<short_goal>, where <short_goal> is a brief, 10-20 character version of the goal that best describes it.
Within this directory, the following files will be generated:
transcript.md: A detailed log of all agent interactions. This includes not just the results of eachWorkItem, but also the detailed internal monologue, discussions, and step-by-step reasoning of the agents as they perform their tasks.report.md: The final, user-facing report. This is a comprehensive, boardroom-quality document that leads with a strong executive summary and includes detailed sections on methodology, macroeconomic analysis, sector deep dives, company profiles, risk analysis, and the final strategic recommendation.
Staged Workflow
-
Initiation:
- The user provides a
GOAL:prompt. - All Agent Personas from
agents.mdare loaded. - A
Runis initiated, and its unique directory is created.
- The user provides a
-
Pre-Read Materials (Optional):
- Process: The framework checks for files in the top-level
/info/directory. - If files exist, the framework lists them and asks the user to select which ones the agents should review for the current run.
- The content of the user-selected files is ingested and becomes the first entry in the
transcript.md, providing a foundational context available to all agents throughout the run. - Output: A "Pre-Read Materials" section at the top of the
transcript.md.
- Process: The framework checks for files in the top-level
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 · 70 lines · 1,188 tokens per session scan A 4a56714e74cc
brain GEMINI.md is an instructions file published in the GitHub repository aliafshar/brain (45 stars, last pushed 11mo ago), licensed Apache-2.0. It adds 1,188 tokens to every session, about $0.0059 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
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).
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.
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.