Borrowing it
Nothing to install: this file belongs to dondai44423/bladebro. 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/dondai44423/bladebro/main/AGENTS.mdgit clone --depth 1 https://github.com/dondai44423/bladebroWrote 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/dondai44423/bladebro/agents-md)<a href="https://agentmods.dev/instructions/dondai44423/bladebro/agents-md"><img src="https://agentmods.dev/badge/instructions/dondai44423/bladebro/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/dondai44423/bladebro/agents-md"><img src="https://agentmods.dev/badge/instructions/dondai44423/bladebro/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 | $0.03152 | $0.03152 |
| Opus 5.5 | $0.01261 | $0.01261 |
| Sonnet 5.5 | $0.00630 | $0.00630 |
| Haiku 4.5 | $0.00315 | $0.00315 |
Grade A, and why
bladebro 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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Before you change anything: read CONTRIBUTING.md. It is one page and it is the binding contract — what PRs are accepted, what gets rejected, and what "verified" means here. This file adds the repo mechanics an agent needs on top of it. If the two ever disagree, CONTRIBUTING.md wins.
Bladebro is an agentic browser driver for AI: an MCP server (bladebro mcp, stdio JSON-RPC) and a CLI (bladebro nav, see, act, …) driving a real Chrome/Chromium over the DevTools Protocol. The shipped artifact is a single Rust binary — no Node.js runtime, no Playwright/Puppeteer, no LLM in the driver. The CDP transport, perception layer, stealth injection, biometrics and session management are built from scratch in this repo.
Two properties shape every change:
- The users are LLMs. Tool outputs, verdicts and error strings get read by an agent mid-task and billed per token. Dense, honest, minimal — a new verbose field is a tax on every user.
- Stealth is measured, not vibed. Every page-visible difference from stock Chrome must be an intentional, documented mask. The instruments below are how that is proven, and they are the bar for merging.
Commands
cargo build --release # → ./target/release/bladebro
cargo fmt --check # formatting (CI-enforced)
cargo clippy --release -- -D warnings # zero warnings, always
cargo test --release # all tests must pass
./target/release/bladebro doctor # environment check
./target/release/bladebro nav example.com # auto-starts its daemon + browser
./target/release/bladebro see content
./target/release/bladebro stop # when done — don't leave a daemon running
Rust: edition 2021, MSRV 1.86. Requirements: Chrome/Chromium installed. On headless Linux bladebro manages its own Xvfb + window manager. Linux (x64 + ARM64), macOS (x64 + arm64) and Windows are all first-class — CI builds all three OSes, so don't write code that silently assumes Linux.
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.
- today Changed b4e2673a89dc
- 5d ago Changed e37afde0f154
- 7d ago Changed 958e594ab8e7
- 10d ago Changed · -2 tokens per session cda929741386
- 14d ago Changed · +3 lines · +357 tokens per session 1b1ad30bd4dd
- 18d ago First seen · 106 lines · 2,797 tokens per session scan A a173b7ec695d
bladebro AGENTS.md is an instructions file published in the GitHub repository dondai44423/bladebro (313 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,152 tokens to every session, about $0.0126 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 2026-09-28.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).