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/protostatis/unbrowser/claude-mdgit clone --depth 1 https://github.com/protostatis/unbrowserWhat 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 | $0.05090 | $0.05090 |
| Opus 5 | $0.02545 | $0.02545 |
| Sonnet 5 | $0.01018 | $0.01018 |
| Haiku 4.5 | $0.00509 | $0.00509 |
Grade A, and why
unbrowser CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| | curl/fetch | LLM WebFetch/Search | unbrowser | Full Chrome | How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
unbrowser
Single statically-linked native binary that gives an LLM a headless browser with real JS execution. No rendering — designed for LLM tool-call use, not human viewing.
Distinct from ~/Projects/sky-search (QuickJS-WASM in user's browser, with iframe rendering for humans). This project ports several JS modules from sky-search but drops rendering, the WebSocket/server layers, and the iframe bridge entirely.
Why this exists
The four-way landscape:
| curl/fetch | LLM WebFetch/Search | unbrowser | Full Chrome | |
|---|---|---|---|---|
| Runs JS | No | No (provider-side, opaque) | Yes (QuickJS) | Yes (V8, JIT) |
| SPA-capable | No | Sometimes | Yes | Yes |
| Interactive (click/type/auth) | No | No | Yes | Yes |
| Session across calls | DIY | No | Yes | Yes |
| Output to LLM | Raw HTML (heavy) | Pre-summarized markdown | BlockMap (semantic, low-token) | Raw DOM or screenshot (very heavy) |
| Memory | ~0 | N/A | tens of MB | 200–500MB+ per page |
| Deploys as | one syscall | API call | one binary | a fleet |
The gap this fills: stateful, JS-required, non-visual web automation for LLM agents — log in, fill forms, navigate SPAs, scrape dashboards, follow multi-step flows — at one-binary deploy cost, with output already shaped for token efficiency.
Positioning: not "Chrome but smaller" (Chrome is the compatibility target — that framing loses). It's "WebFetch but stateful and interactive", or "curl but the page actually runs". The LLM-native output (BlockMap + element refs) is the differentiator that neither curl nor Chrome give you for free.
Honest weak spots vs Chrome: heavy JIT-bound JS (QuickJS is 20–50× slower); anti-bot that fingerprints canvas/WebGL/audio; anything visual (screenshot agents, captcha OCR); sites that lazy-load via real intersection observer + viewport metrics.
Architecture (locked)
- Native, not WASM. Rust host. Crates:
rquickjs,html5ever,wreq(Chrome-fingerprinted HTTP client — see Stealth),tokio,url,serde_json. - Runs page scripts so the DOM settles. SPA-capable.
- Interactive from day one — clicks, typing, event synthesis.
- No rendering. Replacement for human monitoring is a BlockMap: DOM walk → semantic block tree → DDM-style ASCII grid + structured JSON. Same source produces both LLM and human views.
- CSS selectors stay JS-side for v1 (reuse sky-search
dom.js). - Protocol: JSON-RPC over stdin/stdout for commands; NDJSON event stream on stderr for observability.
- Element refs (
e:142) returned by query commands are stable handles into the VDOM. - Stealth is a first-class concern, not a flag. See below.
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 · 164 lines · 5,090 tokens per session scan A 8c5b91ed346f
unbrowser CLAUDE.md is an instructions file published in the GitHub repository protostatis/unbrowser (15 stars, last pushed 11d ago), licensed Apache-2.0. It adds 5,090 tokens to every session, about $0.0255 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
mcp-camoufox AGENTS.md
Instructions for RobithYusuf/mcp-camoufox, covering mcp-camoufox — agent guide, product and repository map, hard constraints, working defaults and architecture invariants.
google-flow-mcp CLAUDE.md
Instructions for roshanarnav25-sloth/google-flow-mcp, covering notes for ai coding agents, what this is, hard rules, before you claim it works and layout.
trusty-squire CLAUDE.md
Instructions for Trusty-Squire/trusty-squire, covering claude.md, project overview, objective function (what this project optimizes for), current state and production, deployed, verified end-to-end.
glovebox-mcp AGENTS.md
Instructions for segentic-lab/glovebox-mcp, covering glovebox-mcp — instructions for the agent, responses: read ok and fix, mental model, the core loop and grounding: how to know where to click.
fanqie-publisher-skill AGENTS.md
Instructions for amm10090/fanqie-publisher-skill, covering fanqie-publisher-skill — codex cli agent adapter, read first, prerequisites, entry points and utf-8 / unicode safeguards.
worbrow AGENTS.md
AGENTS.md instructions for noisystreet/worbrow, covering agents.md, project identity, hard constraints (revert on violation), modifying architecture docs and commit conventions.