gbrain-code AGENTS.md

Repository instructions for GBrain Code, a tool that maps the structure of a code repository. It is intended to inspect status, context, symbols, and changes rather than write code or generate answers.

In plain words
What is it for?
Use it to guide repository status and refresh operations, context mapping, symbol inspection, and diff auditing. It does not cover autonomous editing, chat memory, model consultation, or agent loops.
Why use it?
It keeps repository maps honest by treating connections as navigation clues, requiring exact citations and fresh snapshots, and leaving tests and direct inspection as the authority.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/spacerocket3/gbrain-code/agents-md
Clone the repo
git clone --depth 1 https://github.com/spacerocket3/gbrain-code

Made for: Codex, OpenCode.

Per session 114 This file is loaded in full into every session.
When invoked 114 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00114 $0.00114
Opus 5 $0.00057 $0.00057
Sonnet 5 $0.00023 $0.00023
Haiku 4.5 $0.00011 $0.00011

Measured today against content hash bc1fb8137f56, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gbrain-code 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 today.

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 · 12 lines

What it actually says

Development instructions

GBrain Code is a repository cartographer, not a coding agent or answer generator.

  • Keep its public surface limited to repository status/refresh, context mapping, symbol inspection, and diff auditing.
  • Treat every graph edge as navigation evidence, never proof of runtime behavior.
  • Keep exact citations and snapshot freshness in every consequential result.
  • Do not add model consultation, autonomous editing, chat memory, or agent loops.
  • Retrieval must remain selective, bounded, and honest about unresolved edges.
  • Tests and direct repository inspection remain the source of truth.
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.

  1. today First seen · 12 lines · 114 tokens per session scan A bc1fb8137f56

Subscribe to this mod's changes

gbrain-code AGENTS.md is an instructions file published in the GitHub repository spacerocket3/gbrain-code (0 stars, last pushed today), licensed Apache-2.0. It adds 114 tokens to every session, about $0.0006 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.