obra/superpowers-chrome is a tool that lets coding agents control Chrome browsers directly through the Chrome DevTools Protocol. It supports browser automation through a command-line skill or an MCP server, with the catalogue entries representing ways for agents to use that control.
Borrowing it
Nothing to install: this file belongs to obra/superpowers-chrome. 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/obra/superpowers-chrome/main/CLAUDE.mdgit clone --depth 1 https://github.com/obra/superpowers-chromeWrote 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/obra/superpowers-chrome/claude-md)<a href="https://agentmods.dev/instructions/obra/superpowers-chrome/claude-md"><img src="https://agentmods.dev/badge/instructions/obra/superpowers-chrome/claude-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/obra/superpowers-chrome/claude-md"><img src="https://agentmods.dev/badge/instructions/obra/superpowers-chrome/claude-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 | $0.03399 | $0.03399 |
| Opus 5.5 | $0.01360 | $0.01360 |
| Sonnet 5.5 | $0.00680 | $0.00680 |
| Haiku 4.5 | $0.00340 | $0.00340 |
Grade A, and why
superpowers-chrome CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superpowers Chrome - Developer Documentation
This document contains comprehensive information for maintaining and releasing the superpowers-chrome MCP plugin.
Project Structure
superpowers-chrome/
├── package.json # Root package (version source of truth)
├── mcp/ # MCP server implementation
│ ├── package.json # MCP-specific package (must match root version)
│ ├── src/index.ts # TypeScript source
│ └── dist/index.js # Bundled output (committed to git)
├── skills/ # Claude Code skills
│ └── browsing/
│ ├── chrome-ws-lib.js # Core Chrome CDP library (bundled with MCP)
│ ├── chrome-ws.md # Skill definition
│ └── package.json # Skill metadata (independent version)
├── CHANGELOG.md # Release notes
└── README.md # User documentation
Version Management
Version Numbers
- Root package.json: Source of truth for release version
- mcp/package.json: Must match root version exactly
- skills/browsing/package.json: Independent versioning (skill metadata only)
Version Bumping Rules
Always bump versions together:
- Update root
package.jsonversion - Update
mcp/package.jsonto match - Update
CHANGELOG.mdwith changes - Commit with message:
Bump version to X.Y.Z
Build System
Build Architecture
The MCP server uses a TypeScript → JavaScript → Bundled ESM pipeline:
- Source:
mcp/src/index.ts(TypeScript with imports) - Compile:
tsc→ intermediate JavaScript - Bundle:
esbuild→mcp/dist/index.js(single file, all deps bundled) - External deps:
chrome-ws-lib.jsbundled via relative path
Build Commands
# Full build (from project root)
npm run build
# Equivalent to:
cd mcp && npm install && npm run build
# Which runs:
tsc && esbuild src/index.ts --bundle --platform=node --format=esm --outfile=dist/index.js --external:fsevents
# Clean build
cd mcp && npm run clean && npm run build
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.
- 2mo ago First seen · 394 lines · 3,399 tokens per session scan A ba84d441357f
superpowers-chrome CLAUDE.md is an instructions file published in the GitHub repository obra/superpowers-chrome (371 stars, last pushed 27d ago), licensed MIT. It adds 3,399 tokens to every session, about $0.0136 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 2026-08-30.
superpowers-chrome CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| superpowers-chrome CLAUDE.mdobra/superpowers-chrome | Instructions file | 371 | 27d ago | MIT | A | 3,399 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |