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/nimblebraininc/nimblebrain/agents-mdgit clone --depth 1 https://github.com/NimbleBrainInc/nimblebrainWhat 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 | $0.16577 | $0.16577 |
| Opus 5 | $0.08289 | $0.08289 |
| Sonnet 5 | $0.03315 | $0.03315 |
| Haiku 4.5 | $0.01658 | $0.01658 |
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/`. 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.
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.
- 2d ago First seen · 605 lines · 16,577 tokens per session scan C 473a61d54c13
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.
Other instructions, from other repositories
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
gini-agent CLAUDE.md
Claude Code instructions for Open-Curiosity/gini-agent, a project described as: The agent that remembers and learns.
openscience CLAUDE.md
Claude Code instructions for synthetic-sciences/openscience, covering claude.md: openscience, project overview, repository structure, development and run cli in dev mode.
openscience AGENTS.md
AGENTS.md instructions for synthetic-sciences/openscience, covering style guide, avoid let statements, avoid else statements, prefer single word naming and testing.
beevibe CLAUDE.md
Instructions for beevibe-ai/beevibe, covering beevibe — claude code guide, monorepo structure, running locally, critical: @beevibe/core compiles to dist/ and restarting cleanly.
ralphy CLAUDE.md
Claude Code instructions for alecs5am/ralphy, a project described as: 🎬 Give AI agents tools to create viral videos. Influence at scale, from your terminal.