SkillAgentSearch skills...

OpenCROW

Agentic AI orchestration framework for offensive security and CTF work, with Codex-ready skills, typed MCP servers, workflow CLIs, and OpenCROW Constellation for multi-agent coordination, corpus sync, and final artifact handoff.

Install / Use

claude mcp add 02loveslollipop -- npx -y github:02loveslollipop/OpenCROW

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

69/100

Category

Security

Supported Platforms

Claude Code
Claude Desktop
OpenAI Codex

Our assessment of OpenCROW

OpenCROW scores 69/100 on our quality scale, 1039th of 1,094 Security skills we index.

Its MCP Server is 2.0 KB long, split into 4 sections with 4 code examples: moderately detailed.

It has 10 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
20/30
Structure
15/20
Description
15/15
Adoption
4/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated yesterday, so OpenCROW is actively maintained.
  • Our last check on 2026-10-18 found the source still online.
  • It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 97/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands (2 minor notes below). An AI review of the same text found nothing harmful.

  • noteInstalls by piping a downloaded script into a shellline 12
    curl -fsSL https://opencrow.02labs.me/skills.sh | bash
  • noteInstalls by piping a downloaded script into a shellline 18
    curl -fsSL https://opencrow.02labs.me/install.sh | sudo bash

AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

OpenCROW compared with similar skills

All 4 of these similar skills score higher than OpenCROW; compare them before choosing.

SkillScoreStarsUpdatedFormat
OpenCROW (this skill)by 02loveslollipop69101d agoMCP Server
Agent-Reachby Panniantong100108.3k2d agoCLAUDE.md
headroomby headroomlabs-ai10078.7ktodayCLAUDE.md
CowAgentby zhayujie10047.8k1d agoCLAUDE.md
Scraplingby D4Vinci10093.9ktodayMCP Server

Frequently asked questions

How do I install OpenCROW?
Run claude mcp add 02loveslollipop -- npx -y github:02loveslollipop/OpenCROW. The install tabs above show the steps for each supported agent.
Which AI agents does OpenCROW work with?
It is written for Claude Code, Claude Desktop and OpenAI Codex, as a MCP Server file. Other agents that read the same format can often use it too.
Is OpenCROW safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands (2 minor notes below). An AI review of the same text found nothing harmful. It is Apache-2.0-licensed and scores 97/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is OpenCROW still maintained?
The repository was last updated yesterday, so OpenCROW is actively maintained.

OpenCROW

Portable agent runtime, skills, and multi-provider challenge orchestration.

OpenCROW v2 is a breaking, provider-neutral release for Codex, OpenCode, Claude Code, and Antigravity (agy). It gives each challenge an append-only knowledge lifecycle, portable Agent Skills, typed MCP operations, transactional installation, and an optional trusted multi-agent Constellation runtime.

Quick start

Install only portable skills, hooks, lifecycle MCP, helper Python, and the management command (no sudo):

curl -fsSL https://opencrow.02labs.me/skills.sh | bash

Install the complete framework on a supported Linux host:

curl -fsSL https://opencrow.02labs.me/install.sh | sudo bash

Initialize one local challenge phase after a full installation:

mkdir challenge && cd challenge
opencrow-init codex --challenge-file /path/to/description.txt

The five lifecycle documents are CHALLENGE.md, FINDINGS.md, CHANGELOG.md, HANDOFF.md, and WRITEUP.md. The Original Challenge is immutable; clarifications and all other knowledge are append-only.

Repository layout

  • skills/ — one provider-neutral Agent Skills source tree.
  • packages/lifecycle/ — lifecycle engine, MCP, hooks, prompt, templates, and schemas.
  • packages/mcp/ — common MCP core and domain servers.
  • integrations/ — thin native provider adapters.
  • installer/ — selectors, state transactions, platform maps, and manifests.
  • services/constellation/ — dashboard, backend, provider adapters, and trusted runtime.
  • docs/ — authoritative user, operator, and contributor documentation.

Development

make test
make smoke
make build-releases

See Quick start, installation, challenge lifecycle, and Constellation operations.

The public GitHub Wiki is generated from a manifest-selected subset of repository documentation at stable releases. Direct Wiki edits are overwritten and are not supported.

Related Skills

View on GitHub
GitHub Stars10
CategorySecurity
Updated1d ago
Forks1

Languages

Python

Trust signals

97/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 info