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/onebrain-ai/onebrain/gemini-mdgit clone --depth 1 https://github.com/onebrain-ai/onebrainWrote 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/onebrain-ai/onebrain/gemini-md)<a href="https://agentmods.dev/instructions/onebrain-ai/onebrain/gemini-md"><img src="https://agentmods.dev/badge/instructions/onebrain-ai/onebrain/gemini-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 | $0.00468 | $0.00468 |
| Opus 5 | $0.00234 | $0.00234 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
onebrain 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 4d 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OneBrain — Gemini CLI
OneBrain is a personal AI OS built on a plain-Markdown vault — use its built-in web UI. INSTRUCTIONS.md is written using Claude Code tool names — the mapping below translates them to Gemini CLI equivalents before the shared instructions load.
Load Order
- Tool mapping — translates Claude Code tool names (
Read,Write,Bash, etc.) to Gemini CLI equivalents (read_file,write_file,run_shell_command, etc.) - Shared agent instructions — vault structure, skills, session behavior, and personality
Project-Level Gemini Config
Hooks and slash commands are defined at the project root in .gemini/:
.gemini/settings.json— declarative lifecycle hooks (SessionStart,AfterToolforwrite_file|replace, andAfterAgent) all call theonebrain hookbridge wrapped in a shell-level|| echofail-open fallback (inert once the installed CLI is 3.4.25+; degrades to a harmless stand-in payload when the CLI is missing or older), which otherwise selects behavior from stdin and emits Gemini-compatible{}for no-op/tool events.model.disableLoopDetection: truekeeps legitimate multi-file skill activations from tripping Gemini's repetitive-tool-call heuristic. Version of this content is tracked in the unifiedplugin.jsonalongside the Claude plugin..gemini/commands/onebrain/*.toml— 24 user-facing slash commands under theonebrain:namespace (/onebrain:braindump,/onebrain:capture,/onebrain:research, ...) that activate the matching skill. Namespacing avoids collisions with Gemini built-ins (/help,/tasks) and mirrors the Claude plugin path (.claude/plugins/onebrain/)
Skills, agents, INSTRUCTIONS, and tool-mapping references all live inside the Claude plugin tree at .claude/plugins/onebrain/.... The agent reads them on demand via the paths referenced from each TOML's prompt — no duplication needed.
Tool Name Mapping
@.claude/plugins/onebrain/references/gemini-tools.md
Agent Instructions
@.claude/plugins/onebrain/INSTRUCTIONS.md
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.
- 4d ago First seen · 28 lines · 468 tokens per session scan A 1e2f6444e47d
onebrain GEMINI.md is an instructions file published in the GitHub repository onebrain-ai/onebrain (25 stars, last pushed 6d ago), licensed Apache-2.0. It adds 468 tokens to every session, about $0.0023 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
obsidian-mind CLAUDE.md
Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.
obsidian-mind AGENTS.md
AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.
llm-wiki-compiler AGENTS.md
AGENTS.md instructions for atomicstrata/llm-wiki-compiler, covering llmwiki, development guidelines, code style & standards, clean code rules and comments and documentation.
pi-llm-wiki AGENTS.md
AGENTS.md instructions for zosmaai/pi-llm-wiki, covering agents.md, project, tech stack, file layout and conventions.
DeepPaperNote AGENTS.md
AGENTS.md instructions for 917Dhj/DeepPaperNote, covering deeppapernote agent guide, repository purpose, canonical sources, non-negotiable product invariants and repository structure.
md-redline AGENTS.md
AGENTS.md instructions for dejuknow/md-redline, covering md-redline, repo snapshot, architecture overview, directory layout and behavior that matters.