What is crebain AGENTS.md?

Development instructions for Crebain, a desktop application with a frontend and Tauri wrapper. Tauri packages a web interface as a desktop app, while the guide lists build, lint, formatting, testing, bundle, documentation, and boundary checks.

Use them when developing the frontend or full Tauri app, checking TypeScript, running tests and coverage, verifying responsive layouts, measuring bundle size, and validating documentation or package boundaries.

They make the project’s validation expectations clear before changes are considered ready.

How sepahead/crebain configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to sepahead/crebain. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/sepahead/crebain/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/sepahead/crebain

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sepahead/crebain/agents-md/github.svg)](https://agentmods.dev/instructions/sepahead/crebain/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/sepahead/crebain/agents-md"><img src="https://agentmods.dev/badge/instructions/sepahead/crebain/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sepahead/crebain/agents-md"><img src="https://agentmods.dev/badge/instructions/sepahead/crebain/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,838 This file is loaded in full into every session.

When invoked 3,838 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.03838	$0.03838
Opus 5.5	$0.01535	$0.01535
Sonnet 5.5	$0.00768	$0.00768
Haiku 4.5	$0.00384	$0.00384

Measured 11d ago against content hash 61449aedbaa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

crebain 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 11d 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.

AGENTS.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CREBAIN agent contract

CREBAIN develops standalone 3D simulation, sensor models, visualization, and sensor-fusion research. Its desktop, native environment, and protocol adapters have distinct ownership and evidence contracts. Every completion claim must identify the tested scope and remaining limitations.

Authority and workflow

The owner authorizes agents to commit, push, and merge to main. main has no branch protection. Run the applicable complete gate in Commands and gates before each push. CREBAIN commits are unsigned. The repository configuration sets commit.gpgsign=false. Do not add AI attribution, co-author trailers, or generated-by lines to commits or review descriptions. Releases, tags, and repository settings remain owner actions.

Preserve unrelated changes and another contributor's active scope. Do not publish another owner's changes. The shared checkout can hold another agent's uncommitted work. Use a separate worktree from origin/main. Change a vector or descriptor that Engram shares only in coordination with Engram's owner.

Read before changing

Read README.md first. Then read the document that owns the affected surface:

Surface	Owning documents
Native city, actual observations, renderer lifetime, coupled forks	Native environment
Rapier world, actions, time, complete CPU state, replay	Deterministic dynamics
Local NCP body, numerical kernel, retained responses	Local NCP body, Numerical kernel
Desktop, module ownership, camera delivery	Desktop architecture, Desktop workflows
Sensor fusion, association, covariance, evidence	Sensor fusion, Fusion validation
Models, inference, benchmarks	Model contracts, Detector benchmarks
Scene files, downloads, settings, controls	Configuration, Controls
ROS and Zenoh telemetry	ROS reference, Desktop architecture
Wire-1.0 bridge or advisory producer	Retained NCP bridge, Advisory producer
Engram embedding	Restricted embedding
Host API 2.0 package and recorded NEST work	Host API package
Inert plant components	The applicable `docs/PLANT_*.md` contract and System context
Release or claim changes	Release acceptance, 0.9 release decision, Security

Read the full file on GitHub · 248 lines

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.

11d ago Changed · +3 lines · +64 tokens per session 61449aedbaa4
25d ago Changed · +2 lines · +51 tokens per session 2f62154aafcb
1mo ago Changed · +37 lines · +550 tokens per session aa9ab1d2431b
1mo ago Changed · +1 lines · +44 tokens per session c9b0aaa08453
1mo ago Changed · +3 lines · +94 tokens per session 367b22845327
2mo ago Changed · -22 lines · +85 tokens per session c9b74fd3afe8
2mo ago First seen · 224 lines · 2,950 tokens per session scan A 6a7f1c89ff7e

Subscribe to this mod's changes

crebain AGENTS.md is an instructions file published in the GitHub repository sepahead/crebain (22 stars, last pushed 12d ago), licensed Apache-2.0. It adds 3,838 tokens to every session, about $0.0154 per session on Opus 5.5. 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.

React Rust computer-vision gaussian-splatting sensor-fusion tauri threejs

crebain AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
crebain AGENTS.mdsepahead/crebain	Instructions file	22	12d ago	Apache-2.0	A	3,838	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

crebain: Instructions file for Codex