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/holon-run/webmcp-bridge/agents-mdgit clone --depth 1 https://github.com/holon-run/webmcp-bridgeWrote 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/holon-run/webmcp-bridge/agents-md)<a href="https://agentmods.dev/instructions/holon-run/webmcp-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/holon-run/webmcp-bridge/agents-md.svg" alt="Measured on agentmods" 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 | $0.00614 | $0.00614 |
| Opus 5 | $0.00307 | $0.00307 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
webmcp-bridge 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Mission
webmcp-bridge provides a local-to-browser WebMCP bridge with a unified call path:
local-mcp -> playwright -> browser navigator.modelContext.
The system is native-first and uses shim fallback when a website does not expose native WebMCP.
The architecture is split into:
@webmcp-bridge/local-mcp: local stdio MCP entrypoint (one site session per process) that proxies tool requests to a browser page gateway.@webmcp-bridge/playwright: browser WebMCP page gateway and lifecycle management (native-first, shim fallback).@webmcp-bridge/adapter-*: site-specific fallback tool mapping, used only when native WebMCP is unavailable.@webmcp-bridge/core: shared WebMCP-compatible runtime/shim contracts used by fallback paths.
Current Priorities
- Stabilize stdio MCP semantics in
local-mcp: one-site process lifecycle and strict proxying to Playwright page gateway fortools/listandtools/call. - Harden native-first behavior and shim fallback in
playwright, especially around navigation/frame lifecycle edge cases. - Keep adapters thin and replaceable as fallback-only components; business logic must not leak into shared layers.
- Expand contract coverage for
nativevsshimbehavior before adding new sites/features.
Guardrails
- Do not implement credential vaulting or auth bypass.
- Assume user is already authenticated in browser session.
- Fail closed on ambiguous upstream states (
AUTH_REQUIRED,UPSTREAM_CHANGED, etc.). - Keep MCP payloads JSON-serializable and schema-friendly.
- Preserve single responsibility per package; avoid cross-package implicit coupling.
- Prefer browser-side WebMCP execution for privileged site actions; do not move site credentials into local-mcp.
Coding Rules
- Language: TypeScript ESM, 2-space indentation.
- Every source file must start with a short module header comment describing:
- module responsibility;
- dependency relationship with other modules.
- Prefer small pure utilities and explicit error mapping.
- Avoid introducing site-specific constants into shared packages.
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.
- 4d ago First seen · 50 lines · 614 tokens per session scan A 05552781f893
webmcp-bridge AGENTS.md is an instructions file published in the GitHub repository holon-run/webmcp-bridge (27 stars, last pushed 4mo ago), licensed MIT. It adds 614 tokens to every session, about $0.0031 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
moli AGENTS.md
AGENTS.md instructions for lexmount/moli: Before committing changes that modify Rust source code or Rust build metadata (such as Cargo.toml, Cargo.lock, or rust-toolchain), run all of the following from the repository root and ensure they pass.
apitap CLAUDE.md
Instructions for n1byn1kt/apitap, covering claude.md, using apitap as an mcp tool, commands, architecture and module map.
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.
unbrowser CLAUDE.md
Instructions for protostatis/unbrowser, covering unbrowser, why this exists, architecture (locked), stealth mode (native, on by default) and host functions exposed to js.
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.
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.