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/garrytan/gbrain/agents-mdgit clone --depth 1 https://github.com/garrytan/gbrainWhat 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 | $0.02524 | $0.02524 |
| Opus 5 | $0.01262 | $0.01262 |
| Sonnet 5 | $0.00505 | $0.00505 |
| Haiku 4.5 | $0.00252 | $0.00252 |
Grade C, and why
gbrain AGENTS.md scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://bun.sh/install | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://bun.sh/install | bash How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents working on GBrain
This is your install + operating protocol. Claude Code reads ./CLAUDE.md automatically.
Everyone else (Codex, Cursor, OpenClaw, Aider, Continue, or an LLM fetching via URL):
start here.
Becoming someone's persistent personal agent (identity + memory + private repo)? Follow
BOOTSTRAP_FOR_AGENTS.md— thegbrain bootstrapflow — instead of the plain install below, then come back here for the operating protocol. Connecting to an EXISTING remote brain from a laptop agent?gbrain connect https://your-host/mcp --token gbrain_xxx --install(see the MCP table inREADME.md).
Install (5 min)
- Install gbrain via Bun (the canonical path):
Ifcurl -fsSL https://bun.sh/install | bash export PATH="$HOME/.bun/bin:$PATH" bun install -g github:garrytan/gbrainbun install -gaborts orgbrain doctorreportsschema_version: 0, the CLI prints a recovery hint pointing at #218. Rungbrain apply-migrations --yesto recover, or fall back to the deterministic install:git clone https://github.com/garrytan/gbrain.git ~/gbrain && cd ~/gbrain && bun install && bun link. - Init the brain:
gbrain init(defaults to PGLite, zero-config). For 1000+ files or multi-machine sync, init suggests Postgres + pgvector via Supabase. - STOP — ask the user about search mode.
gbrain initauto-applied a default but printed a 9-cell cost matrix (mode × downstream model) preceded by[AGENT]markers. You MUST relay the matrix to the operator and confirm their choice before continuing. Cost spread between corners is 25x — silent acceptance is the wrong default. See./INSTALL_FOR_AGENTS.mdStep 3.5 for the exact ask-the-user protocol. Same banner fires ongbrain post-upgradefor existing users (search modes were added in v0.32.3). - Read
./INSTALL_FOR_AGENTS.mdfor the full step-by-step flow (API keys, identity, cron, verification).
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 · 158 lines · 2,524 tokens per session scan C a436b2f63639
gbrain AGENTS.md is an instructions file published in the GitHub repository garrytan/gbrain (29,316 stars, last pushed 2d ago), licensed MIT. It adds 2,524 tokens to every session, about $0.0126 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.