Ironheights

Frank-Masciopinto/ironheights

Offline security scanner that protects any AI bot's skills: scans any skill folder with a SKILL.md (including Gemini CLI skills in ~/.gemini/skills/) for prompt injection, credential theft, and other risky patterns before you install it, with findings tagged by OWASP LLM Top 10 and OpenCRE ID. Reads files as data, never runs them, no telemetry. Run npx ironheights scan ./path/to/skill. Apache-2.0

TypeScript Apache-2.0

View on GitHub → Find it in the atlas

Install

npm install -g ironheights

Repository reader

Explore before you clone

Read the project’s README, skills and supporting Markdown here. Rendered view is shown first; source is one click away when you need the exact text.

Fetched from GitHub
Open on GitHub
Loading the project’s README…

Public files are loaded on demand from the repository. The atlas does not copy or modify them.

Screenshot

Screenshot or social card for Ironheights
GitHub's social card — no screenshot was found for this project, fetched from source rather than copied into this repository.

Platform support

Derived from the project's own README, install route, CI configuration and release assets — not from running it.
PlatformRuns hereOn what evidence
WindowsNoNo evidence of support anywhere in the project.
WSL2LikelyInferred from the language or runtime. Nothing in the project says so.
macOSYesStated in the project's own README, install route, CI config or release assets.
LinuxYesStated in the project's own README, install route, CI config or release assets.
DockerNoNo evidence of support anywhere in the project.

Where it came from

Named by 2 of the 39 lists the atlas merges, independently of each other.

  • AI Agents (Jenqyang)
  • Gemini CLI Ecosystem

How it is classified

One topic, 5 harnesses. Each link is a prerendered page of everything else in that slice.

Frameworks & SDKsClaude / AnthropicMCPCodex / OpenAIGemini / GoogleCursor

Related in Frameworks & SDKs

Closest first — projects that plug into the same harnesses, then the ones the most lists agreed on.

  • EGCFmarzochi/EGCPersistent cross-session memory MCP server for 13+ AI coding tools. SQLite-backed state survives context resets and keeps Claude Code, Cursor…
  • Strands Agents SDKstrands-agents/harness-sdkAWS's open-source, model-driven agent SDK that treats the loop, tool binding, and guardrails as first-class primitives. Supports Bedrock, Anthropic…
  • AIWGjmagly/aiwgDeploys versioned agents, skills, rules, and governed workflows into the native project paths used by Claude Code, Codex, Copilot, Cursor, and other…
  • Speakeasy control planespeakeasy-api/gramMCP gateway that scopes agent tool access by identity, team, and role, with security policy enforced on each action and an audit trail. Useful as a…
  • Claudexorrazzant/claudexorRoutes one coding thread across harnesses with quota-aware rotation between subscription profiles, Best-of-N runs, and cross-family review.
  • AgentifyMonadWorks/agentifyCLI tool that transforms any OpenAPI spec into 9 agent interface formats (MCP server, AGENTS.md, CLAUDE.md, .cursorrules, Skills, llms.txt…
  • browser-harnessbrowser-use/browser-harnessSelf-healing browser harness that connects an LLM directly to your real Chrome via CDP. The critical design decision: the agent itself writes…
  • Riusglassflow/rius-sdk-pythonMIT Python SDK that traces LLM calls, tool calls and agent steps as OpenTelemetry GenAI spans, with auto-instrumentation for OpenAI, Anthropic…