pinchtab-mcp: Instructions file for Codex

AGENTS.md

pinchtab-mcp AGENTS.md is an instructions file for Codex, OpenCode from maderwin/pinchtab-mcp. It costs 728 tokens per session, scanned A, original, MIT.

A set of project instructions for developing pinchtab-mcp, an MCP server that controls a browser. It documents project structure, design decisions, browser interaction rules, and recommended workflows.

In plain words
What is it for?
Use it when modifying pinchtab-mcp, especially its tools, browser navigation, element references, startup behavior, logging, or code style.
Why use it?
It gives coding agents the project-specific rules they need to make compatible changes and avoid stale browser references or incorrect tool usage.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is maderwin/pinchtab-mcp's own configuration. It tells Codex and OpenCode how to work on pinchtab-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pinchtab-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to maderwin/pinchtab-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/maderwin/pinchtab-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/maderwin/pinchtab-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for pinchtab-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/maderwin/pinchtab-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/maderwin/pinchtab-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/maderwin/pinchtab-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/maderwin/pinchtab-mcp/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.

agentmods 80×15 button for pinchtab-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/maderwin/pinchtab-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/maderwin/pinchtab-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 728 This file is loaded in full into every session.
When invoked 728 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00728 $0.00728
Opus 5.5 $0.00291 $0.00291
Sonnet 5.5 $0.00146 $0.00146
Haiku 4.5 $0.00073 $0.00073

Measured 2mo ago against content hash b142a31d623d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pinchtab-mcp 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 2mo 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 · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guidelines for pinchtab-mcp

For project structure, tools, configuration, and code style see PROJECT_INDEX.md.

Key Decisions (Non-Obvious)

  • McpServer, not Server — uses registerTool() + zod schemas from @modelcontextprotocol/sdk/server/mcp.js. The Server class is deprecated.
  • Auto-start — PinchTab binary starts on first API call. Lookup order: PINCHTAB_BIN env → node_modules/.bin/pinchtab → system PATH.
  • Stdio transport — MCP over stdin/stdout. All logging → stderr (console.error).
  • Element refs — e0, e1, … are accessibility tree identifiers, not DOM selectors. They exist only in snapshot responses, not in the DOM. Stale after navigation or major DOM changes.
  • No null — the codebase uses undefined everywhere (including toJson(): JSON.stringify(value, undefined, 2)).
  • Sorted keys — all object literals have alphabetically sorted keys, including z.object() fields and MCP tool config objects.
  • Real interactions by default — humanClick (real mouse events) and humanType (character-by-character) are defaults. Programmatic variants are opt-in fallbacks.
  1. Navigate with waitMs to get a snapshot in one call: pinchtab_navigate({ url, waitMs: 3000 }).
  2. Prefer snapshot over screenshot — snapshot costs ~3K tokens, screenshot costs 10-50K+ tokens. Use screenshot only when visual layout matters.
  3. Use filter='interactive' for snapshot when you only need buttons/links/inputs.
  4. Click with waitMs to get post-click state in one call: pinchtab_click({ ref, waitMs: 1000 }).
  5. Wait for dynamic content with pinchtab_wait_for_selector({ selector: '.loaded' }) instead of fixed delays.
  6. React/Vue/Angular forms — use clearFirst: true in pinchtab_type to properly trigger framework state updates.
  7. Avoid stale refs — always re-snapshot after navigation or major DOM changes.

When Modifying Tools

  1. Correct file: src/tools/{instances,navigation,interaction,content}.ts.
  2. Pattern: server.registerTool(name, { description, inputSchema, title }, handler) — keys sorted.
  3. inputSchema: z.object({...}) with fields sorted alphabetically.
  4. Name prefix: pinchtab_.
  5. Return format: { content: [{ text, type: "text" as const }] } — keys sorted.
  6. Use toJson(result) from ../utils.js for pretty-printing, never JSON.stringify(x, null, 2) directly.
  7. Use pinch(method, path, body?) from ../pinchtab/client.js for all HTTP calls.

Read the full file on GitHub · 39 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. 2mo ago First seen · 39 lines · 728 tokens per session scan A b142a31d623d

Subscribe to this mod's changes

pinchtab-mcp AGENTS.md is an instructions file published in the GitHub repository maderwin/pinchtab-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 728 tokens to every session, about $0.0029 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 2026-08-31.

Related

pinchtab-mcp AGENTS.md compared with instructions from other repositories

pinchtab-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pinchtab-mcp AGENTS.mdmaderwin/pinchtab-mcpInstructions file05mo agoMITA728Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot