agentmods.dev

browser AGENTS.md

Repository instructions for AI coding agents working on a browser project. They explain pull-request naming rules, required checks, and the project’s contribution workflow.

In plain words
What is it for?
Use them before opening a pull request to format and check Rust code, choose a valid Conventional Commit title, keep changes focused, and record the model or tools used.
Why use it?
They reduce failed continuous-integration checks and make changes easier to review and release correctly.

Instructions file for CodexOpenCode

127 1mo ago A scan 674 tokens original MIT
View the source file lucid-softworks/browser
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/lucid-softworks/browser/agents-md
Clone the repo
git clone --depth 1 https://github.com/lucid-softworks/browser

Made for: Codex, OpenCode.

Per session 674 This file is loaded in full into every session.
When invoked 674 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00674 $0.00674
Opus 5 $0.00337 $0.00337
Sonnet 5 $0.00135 $0.00135
Haiku 4.5 $0.00067 $0.00067

Measured 3d ago against content hash 13dd0bd44553, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browser 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 3d 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 · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Conventions for AI coding agents (and humans driving them) working in this repo. This file is the quick, actionable contract; see README.md for architecture and the PR template for the checklist.

Pull requests

  • The PR title MUST be a Conventional Commit. PRs are squash-merged, so the title becomes the commit message and drives automatic versioning (release-plz). A non-conforming title fails CI (amannn/action-semantic-pull-request).
    • Format: type(scope): summary — e.g. feat(css): support aspect-ratio, fix(url): strip tab/newline before parsing, ci: cache the prebuilt V8 static lib.
    • Allowed types: feat, fix, docs, style, refactor, perf, test, build, ci, chore, revert.
    • Scope is optional but preferred; use the crate name (engine, dom, css, url, …).
    • Keep one PR to one logical change so the squashed title describes it honestly.
  • Note which model/tooling produced the PR (this project is LLM-first — prefer changes authored by a capable coding model and reviewed by a human).

Before you open a PR

Run, from the workspace root:

cargo fmt --all
cargo clippy --workspace        # must be clean (warnings are denied in CI)
cargo test --workspace          # CI runs this on macOS / Linux / Windows

Guiding constraint

The eventual goal is to rewrite everything in Rust, including the parts currently reused. Every reused crate is walled off behind our own module boundary (net::fetch, paint::GlyphRasterizer, js::Runtime, …) so swapping it for a hand-written implementation later is a localized change. When adding a dependency, keep it behind such a boundary and prefer pure-Rust crates.

Web Platform Tests (conformance)

  • Never edit WPT tests to make them pass — fix the engine. The vendored tests are the spec oracle; changing them defeats the purpose. (Engine unit tests may change freely.)
  • Run the suite locally the way other browsers are tested — the real wpt run harness driving the engine over WebDriver: 
    scripts/run-wpt.sh dom/nodes        # an area, dir, or single test file
    See docs/running-wpt.md for one-time setup (WPT checkout + hosts).
  • CI runs the WPT conformance suite on PRs that can affect it; don't regress it.

Read the full file on GitHub · 54 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.

  1. 3d ago First seen · 54 lines · 674 tokens per session scan A 13dd0bd44553

Subscribe to this mod's changes

browser AGENTS.md is an instructions file published in the GitHub repository lucid-softworks/browser (127 stars, last pushed 1mo ago), licensed MIT. It adds 674 tokens to every session, about $0.0034 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 2026-08-30.

From ScratchGit and workflowappkitbrowser-enginecssdom
Related

Other instructions, from other repositories

starling AGENTS.md

Instructions for starling-browser/starling, covering agents — rules of engagement, tl;dr, 1. orient, 2. claim something unblocked and 3. read the package file and start working on main.

starling-browser/starling · 5,796 tokens

starling CLAUDE.md

Instructions for starling-browser/starling: The repository's agent rules of engagement live in AGENTS.md — read it first.

starling-browser/starling · 329 tokens

electron CLAUDE.md

Instructions for electron/electron, covering electron development guide, running nodemodules binaries, project overview, directory structure and build tools setup.

electron/electron · 2,653 tokens

webgradients AGENTS.md

Instructions for itmeo/webgradients, covering agents.md, files and what they're for, why gradients.json only had 11 entries until now, webgradients.css structure and gradients-parsed.json / gradients.json structure.

itmeo/webgradients · 1,579 tokens

html-video CLAUDE.md

Instructions for nexu-io/html-video, covering html-video 项目工作区, 角色与边界, 产品定位（决策时间线）, 关键差异化 vs hyperframes and 目录结构.

nexu-io/html-video · 6,229 tokens

react-svg AGENTS.md

Instructions for tanem/react-svg, covering agents.md, writing, architecture, build & test and releases.

tanem/react-svg · 1,330 tokens