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/tidesurf/core/agents-mdgit clone --depth 1 https://github.com/TideSurf/coreWhat 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 | $0.01164 | $0.01164 |
| Opus 5 | $0.00582 | $0.00582 |
| Sonnet 5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
core 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 yesterday.
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TideSurf Agent Guide
Read this before editing the repo. CLAUDE.md points here so Claude, Codex, and other agents share one source of truth.
Project
TideSurf is a TypeScript library and stateful CLI that connects Chromium to agents. It launches or connects through CDP, compresses the live DOM into token-efficient text, and exposes one shared tool registry through the SDK, CLI, and MCP adapter.
Architecture
src/
tidesurf.ts main TideSurf class
cli.ts lightweight CLI and daemon bootstrap
cli-program.ts command dispatch and MCP stdio mode
cli/ argument parsing, browser controller, session IPC, daemon
index.ts public API exports
types.ts shared CDP, parser, and tool types
errors.ts typed error hierarchy
validation.ts URL, selector, expression, and element ID validation
cdp/ Chrome launch, connection, page, tabs, retries, timeouts
parser/ DOM walk, classify, assign IDs, serialize, budget tokens
tools/ canonical tool registry and executor
extensions/ Agent Plugins and Agent Skills loading, discovery, validation
mcp/ thin optional-dependency adapter and plugin MCP proxy
website/
landing/ TideSurf landing page
docs/ TideSurf documentation app
The package root is also a shipped Agent Plugins directory: plugin.json, mcp.json, and skills/ are published so compatible clients can install TideSurf directly.
Commands
Run from the repo root unless a command says otherwise.
bun install
bun run build
bun run typecheck
bun run typecheck:examples
bun run test
bun run test:integration
bun run test:bench
bun run check:docs
bun run build:web:landing
bun run build:web:docs
bun run smoke:pack
bun run verify:release
For local website work, use the package scripts directly:
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.
- yesterday First seen · 103 lines · 1,164 tokens per session scan A e4a0391abc1b
core AGENTS.md is an instructions file published in the GitHub repository TideSurf/core (21 stars, last pushed 15d ago), licensed Apache-2.0. It adds 1,164 tokens to every session, about $0.0058 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.
Other instructions, from other repositories
open-browser-use AGENTS.md
Instructions for iFurySt/open-browser-use, covering open-browser-use, 每轮开始先读, 代码改完前要读, 按任务需要选读 and 工作规则.
open-browser-use CLAUDE.md
Instructions for iFurySt/open-browser-use, a project described as: 🔮 Platform-neutral Browser Use for AI agents: real Chrome automation with a CLI + SDKs, no lock-in, dead simple.
browser-harness CLAUDE.md
Instructions for browser-use/browser-harness, a project described as: Browser Harness | Self-healing harness that enables LLMs to complete any task.
terminal AGENTS.md
Instructions for browser-use/terminal, covering agent notes, rust rewrite verification loop and terminal ui testing standard.
browser-use CLAUDE.md
Instructions for browser-use/browser-use, covering claude.md, high-level architecture, core components, event-driven browser management and cdp integration.
obscura AGENTS.md
Instructions for h4ckf0r0day/obscura, covering agents.md, build, rendering and stealth, no rendering, with rustls or stealth and test.