Borrowing it
Nothing to install: this file belongs to unbrowse-ai/unbrowse. 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/unbrowse-ai/unbrowse/main/AGENTS.mdgit clone --depth 1 https://github.com/unbrowse-ai/unbrowseWrote 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/unbrowse-ai/unbrowse/agents-md)<a href="https://agentmods.dev/instructions/unbrowse-ai/unbrowse/agents-md"><img src="https://agentmods.dev/badge/instructions/unbrowse-ai/unbrowse/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/unbrowse-ai/unbrowse/agents-md"><img src="https://agentmods.dev/badge/instructions/unbrowse-ai/unbrowse/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 | $0.00438 | $0.00438 |
| Opus 5.5 | $0.00175 | $0.00175 |
| Sonnet 5.5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
unbrowse 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 18d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- unbrowse CLAUDE.md — 100% identical, 0 lines differ
What it actually says
READ ~/.claude/AGENTS.md BEFORE ANYTHING (skip if missing).
unbrowse (client) — guide for agents
Open-source client for the hosted Unbrowse REST API (/api/v1) and remote MCP. No browser, no site logic; unbrowse mcp is only a stdio proxy to the hosted MCP.
| Path | Owns |
|---|---|
packages/sdk |
@unbrowse/sdk: every /api/v1 route. client and types maintained here; only mcp-install.ts is source-synced |
packages/cli |
unbrowse CLI on the SDK (bundled in). auth.ts: API key and OAuth storage |
skill/SKILL.md |
Agent contract, from unbrowse6 skill/; shipped in the CLI package and every plugin |
plugins/<host> |
Claude Code, Codex, Grok Build, OpenClaw, Hermes, elizaOS plugins. Skill and shared hook scripts are copies: edit sources, run node scripts/sync-plugins.mjs |
docs/ |
User docs and the whitepaper |
Commands: bun install · bun test ./packages ./tests · bun run check:plugins · bun run typecheck · bun run build · bun run cli help.
Rules:
- A new API route gets an SDK method and a row in
packages/sdk/tests/client.test.ts; a CLI command maps to one SDK method. - Never accept, log or print a password or token.
- Built output runs on plain Node 18.17+.
- Root CLAUDE.md is a byte copy of this file.
Money gap: a new user can install the right client and complete a first hosted request.
Root CLAUDE.md and AGENTS.md must be identical. No nested agent instruction files.
Public boundary: docs/public-sync.md. Verify with bun run check:public (PUBLIC_SURFACE_OK), then tests and packed-client smoke. Read package MODULE.md before editing.
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.
- 18d ago First seen · 28 lines · 438 tokens per session scan A ebe0fcda6efe
unbrowse AGENTS.md is an instructions file published in the GitHub repository unbrowse-ai/unbrowse (794 stars, last pushed yesterday), licensed MIT. It adds 438 tokens to every session, about $0.0018 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).