Borrowing it
Nothing to install: this file belongs to MGrin/bb-plugin-system. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MGrin/bb-plugin-system/main/AGENTS.mdgit clone --depth 1 https://github.com/MGrin/bb-plugin-systemWrote 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/mgrin/bb-plugin-system/agents-md)<a href="https://agentmods.dev/instructions/mgrin/bb-plugin-system/agents-md"><img src="https://agentmods.dev/badge/instructions/mgrin/bb-plugin-system/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.
<a href="https://agentmods.dev/instructions/mgrin/bb-plugin-system/agents-md"><img src="https://agentmods.dev/badge/instructions/mgrin/bb-plugin-system/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00790 | $0.00790 |
| Opus 5 | $0.00395 | $0.00395 |
| Sonnet 5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
bb-plugin-system 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 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.
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — bb-plugin-system
A bb plugin showing what the machine is doing while agents work it: a System panel,
homepage tiles and a bb system CLI, with 24h of per-machine history.
README.md is the user-facing document, and its "How it measures" section
is the part to read before touching a metric — every reading in this plugin was chosen
against a wrong one that looked right.
Commands, all run 2026-09-09
npm install # rc=0
npm test # node --test over lib/*.test.ts — 12 tests, 0 fail
npm run typecheck # tsc --noEmit, rc=0
bb plugin build . # dist/{server,app}.js + .meta.json + app.css
The gate
Those two scripts plus three GitHub Actions workflows: test.yml, typecheck.yml and
managed-install.yml. The last is the one a green local run cannot stand in for — bb's
managed git install resolves runtime dependencies only
(npm install --omit=dev --omit=optional --ignore-scripts) and then builds, so a module
imported at runtime but parked in devDependencies works here and fails for every real
user. systeminformation, the Radix/Hugeicons UI packages and zod are runtime and sit
in dependencies for exactly that reason; better-sqlite3 and hono are types-only and
must not move.
Layout
| path | what it is |
|---|---|
server.ts |
sampler, ring buffer, bb system commands, remote-machine sampling |
lib/ |
the pieces with their own tests (battery.ts), plus UI helpers |
app.tsx, components/, hooks/ |
the panel and the homepage tiles |
components.json |
shadcn config — components/ui/** is generated, do not hand-edit |
Conventions that differ from the defaults
- Tests are
node --test --experimental-strip-typesoverlib/*.test.ts. A new suite outsidelib/is invisible tonpm test; put it there or widen the glob deliberately. - A metric must name its basis. Memory is Activity Monitor's
(
anonymous - purgeable + wired + compressed), CPU is real tick-delta utilization, and pressure is the kernel signal reported separately. The obvious alternatives were measured and are wrong — see the README before replacing one. - Sampling is adaptive on purpose — 15s while a thread is running a turn or the panel is open, 60s otherwise, driven by what bb knows about live work. A fixed short interval is not a simplification; it collects data nobody is reading and fights timer coalescing.
- Top processes shell
psdirectly, deliberately, rather than going throughsysteminformation— which runs the same command and takes its decayedpcpuverbatim. - A remote machine is sampled through its own bb daemon, never by reading this process's filesystem. macOS is the tested platform; Linux is supported remotely; Windows machines list but cannot be sampled.
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 · 61 lines · 790 tokens per session scan A 9e945ad229fa
bb-plugin-system AGENTS.md is an instructions file published in the GitHub repository MGrin/bb-plugin-system (3 stars, last pushed 3d ago), licensed MIT. It adds 790 tokens to every session, about $0.0040 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 2026-09-10.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).