Zimreaper — Development skill for Claude Code
Agentic browser for bug bounty: Claude, Hermes or Codex drives real Chromium over MCP.
How to install Zimreaper
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Mr-Destroyer/ZIMREAPER and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Zimreaper does
Agentic browser for bug bounty: Claude, Hermes or Codex drives real Chromium over MCP.
Alternatives in Development
- Domxss — Confirm DOM XSS in a real headless browser — injects canary payloads into params + URL fragment and only repor 4.5k ★
- Agentic Stack — One brain, many harnesses 2.2k ★
- /report — Generate a submission-ready bug bounty report 1.8k ★
README
**A real Chromium browser that an AI agent drives with a real mouse, a real keyboard and a real wheel — over MCP — built for bug hunting.**
[](https://github.com/Mr-Destroyer/ZIMREAPER/actions/workflows/ci.yml) [](LICENSE) [](#build-from-source) [](#install) [](#the-21-tools) [](docs/protocol.md)
[Install](#install) · [Connect an agent](#connect-your-agent) · [Tools](#the-21-tools) · [Bug bounty](#built-for-bug-bounty) · [Trust boundary](#the-trust-boundary) · [Troubleshooting](#troubleshooting)
Most "AI browser" projects call `element.click()` from a script and hope the page believes it. Frameworks check `isTrusted`, bot walls score the event trail, and half the app never notices. ZIMREAPER drives Chromium the way a person does: `Input.dispatchMouseEvent` with real press/release/click counts, real key events with proper codes and modifiers, real wheel deltas, real drag paths. Every click you see in the audit log actually happened in the compositor.
On top of that it gives the agent senses a person does not have: a token-budgeted accessibility snapshot with stable refs, diffs instead of re-reads, a network log of the XHRs the SPA actually made, forked sessions that share one login, and replayable traces that refuse to click when the p
Related Skills
RuneSpace
A browser-first sci-fi RPG centered on skill grinds, crafting, and server-authoritative loops. Built with agen
Cranibox
Cranibox — anytime, anywhere, every device: a self-hosted, trusted Agent Brain. Run Codex, Claude Code & Herme
Triager
Evaluate a bug bounty report before submission by critiquing it from the perspective of a real triager. Use th
Open Claude In Chrome
Claude in Chrome, reverse-engineered and open-source. No domain blocklist. Any Chromium browser. Same 18 MCP t
Leapfrog MCP
Multi-session browser MCP server -- 15 parallel isolated Chromium sessions so multiple Claude Code terminals c
Lab Agent
Research topic-selection platform. Drives the agent already installed on your machine (pi / Claude Code / Code
Related Agents
Manual QA
Use when a change needs to be exercised in a real running app — not unit tests, but a human-style check of the
QA Explorer
Hands-on exploratory tester that drives the RUNNING application (browser via Playwright MCP / Claude in Chrome
Beardrive Admin
Usability evaluator playing the ADMIN persona on a self-hosted BearDrive hub — an IT admin deploying BearDrive