What is worbrow AGENTS.md?

Repository instructions for coding agents and people working on worbrow, a Rust command-line and library project that gives AI agents web search through local browsers. They define the project structure, required design documents, output format, and rules for changes.

Guiding work on worbrow, including changes to its Rust layers, browser drivers, JSON output contract, architecture documents, and commits.

They reduce accidental architecture violations and make important checks and commit expectations visible before code is changed.

How noisystreet/worbrow configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to noisystreet/worbrow. 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/noisystreet/worbrow/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/noisystreet/worbrow

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/noisystreet/worbrow/agents-md/github.svg)](https://agentmods.dev/instructions/noisystreet/worbrow/agents-md)

Your own site

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

Per session 665 This file is loaded in full into every session.

When invoked 665 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	$0.00665	$0.00665
Opus 5.5	$0.00266	$0.00266
Sonnet 5.5	$0.00133	$0.00133
Haiku 4.5	$0.00067	$0.00067

Measured 2mo ago against content hash 20cec01af7e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

worbrow 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 2mo 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 · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Hard constraints and verification entry points for agents (and humans) working in this repository.

Project identity

Rust (edition 2024, MSRV 1.97) CLI tool, binary name worbrow, library name worbrow
Provides "web search" capability for AI agents: drives local headless browsers, outputs a stable JSON contract
Architecture authority: docs/design.md (§5 layering, §6 modules, §7 contract, ADR section)

Hard constraints (revert on violation)

Dependency direction: cli → app → domain/ports ← adapters(drivers/engines). domain has no IO / browser / parser-framework dependencies (serde + chrono for DTO serialization only); app programs only against the ports traits; reverse/cyclic dependencies are forbidden.
Hand-written browser protocols: CDP (Chrome/Edge) and Marionette (Firefox) must be implemented by hand; introducing chromiumoxide / fantoccini / playwright is forbidden. Protocol commands live in their own driver files plus the shared JSON-RPC framework in drivers/jsonrpc.rs. The only exception: revisit per docs/design.md when V2 deep control is needed.
Output contract: stdout only carries JSON (success/failure payloads); the schema_version field only grows, never changes; logs always go to stderr. Breaking the contract requires bumping the schema major version and recording an ADR.
Engine adapters: adding an engine = a new file + one registration line in engines/mod.rs; parse failures go through EngineFailure (engine_error/exit 4); never patch by changing the schema.
Exit-code semantics frozen (0/2/3/4/124/1), see src/error.rs::exit_code.
Safety red lines: no secrets written, no permission bypass, no automatic visits to third-party URLs in search results (output only).

Modifying architecture docs

Major structural changes to docs/design.md (layering, ADRs, contract) require user confirmation before changing; small fixes (typos, numbering) can be made directly.
New decisions are recorded as ADRs: append to docs/adr/NNNN-title.md (docs/design.md §4 is the index table; format follows the docs-style template).

Read the full file on GitHub · 53 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.

2mo ago First seen · 53 lines · 665 tokens per session scan A 20cec01af7e9

Subscribe to this mod's changes

worbrow AGENTS.md is an instructions file published in the GitHub repository noisystreet/worbrow (1 stars, last pushed 11d ago), licensed Apache-2.0. It adds 665 tokens to every session, about $0.0027 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 2026-08-31.

Browser automation Languages Rust agent browser-automation chrome cli firefox headless-browser

worbrow AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
worbrow AGENTS.mdnoisystreet/worbrow	Instructions file	1	11d ago	Apache-2.0	A	665	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

worbrow: Instructions file for Codex