nimblebrain AGENTS.md

A set of repository instructions for NimbleBrain, a self-hosted platform for tool connections, interactive interfaces, scheduled runs, and multiple AI agents.

In plain words
What is it for?
It is for guiding implementation, local builds, verification, worktree development, conventions, and tests.
Why use it?
It gives a coding assistant the project's build, testing, worktree, and style rules in one place.

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/nimblebraininc/nimblebrain/agents-md
Clone the repo
git clone --depth 1 https://github.com/NimbleBrainInc/nimblebrain

Made for: Codex, OpenCode.

Per session 16,577 This file is loaded in full into every session.
When invoked 16,577 The same file — it is already loaded in full.
Security scan C 2 findings. Scan, not verified.
Origin unknown 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 $0.16577 $0.16577
Opus 5 $0.08289 $0.08289
Sonnet 5 $0.03315 $0.03315
Haiku 4.5 $0.01658 $0.01658

Measured 2d ago against content hash 473a61d54c13, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

nimblebrain 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

Each worktree gets its own isolated state, so two worktrees can run side-by-side without colliding. Reset with `rm -rf .nimblebrain-worktree && bun run dev:worktree`. Share state across worktrees with `NB_WORK_DIR=/abs/p

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

**Classification rule:** If a test calls `Runtime.start()`, `startServer()`, `Bun.serve()`, or `spawnSync()`, it belongs in `test/integration/`. Everything else goes in `test/unit/`.
AGENTS.md · 605 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 2d ago First seen · 605 lines · 16,577 tokens per session scan C 473a61d54c13

Subscribe to this mod's changes

nimblebrain AGENTS.md is an instructions file published in the GitHub repository NimbleBrainInc/nimblebrain (19 stars, last pushed 4d ago), with no licence file. It adds 16,577 tokens to every session, about $0.0829 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.