By endorlabs
Legacy Claude Code plugin id for Endor Labs Agent Kit workflows.
Parse Endor AI SAST findings, use exploit reproduction and remediation guidance as patch context, fetch source at the pinned commit, and open change requests when requested.
Use this agent when the user asks whether to add, upgrade, or use a specific package version. Examples: "Is lodash 4.17.20 safe?", "Should I use requests 2.28.0?", "Check log4j-core 2.14.1 before I add it." Returns a dependency verdict with evidence, conditions, alternatives, and any data gaps.
Use this agent when the user needs help diagnosing and fixing Endor Labs errors, warnings, missing integrations, scan failures, slow scans, or unhealthy configuration. Endor Troubleshooter gathers the smallest useful read-only Endor evidence, classifies the issue across scan, integration, authentication, dependency resolution, container, reachability, policy, and workflow lanes, then returns low-friction repair guidance without mutating Endor, source-provider, or repository state.
Use this agent when a customer needs rapid read-only response to a software supply-chain malware incident. It gathers or ingests current malware intelligence, normalizes affected package and version evidence, and correlates that evidence against Endor Labs tenant package inventory across a namespace and child namespaces. It reports confirmed exposure, possible exposure, unaffected scope, indicators of compromise, remediation guidance, and future action contracts without mutating Endor Labs or source systems.
Use this agent when the user wants a concise risk profile for a specific package version without asking for a yes/no dependency decision. Examples: "Summarize npm lodash 4.17.20 risk", "Give me the risk picture for log4j-core 2.14.1", "What should I know about this package version before I review it?" Returns an evidence-backed package risk summary with vulnerabilities, malware or typosquat signals, package scores, license notes, recommended next checks, and any data gaps.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Ready-to-use Endor Labs agents for AI coding assistants, plus the recipe-first builder used to maintain and publish them.
[!TIP] Pick a lane first. The repository is both an installable agent catalog and the source generator for the public
endorlabs/ai-pluginsmirror.
| I want to... | Go here |
|---|---|
| 🚀 Install agents in a coding assistant | docs/getting-started.md or the host package README |
| 🧰 Contribute or propose an agent | docs/contributing-agents.md |
| 🤖 Ask an agent to inspect or sync this repo | docs/for-agents.md |
| 🧰 Change how agents are generated | docs/maintainer-guide.md |
📦 Publish or mirror to ai-plugins | docs/distribution-sync.md |
| 🧱 Embed the workflows in another runtime | docs/portable-runtime-conformance.md |
A machine-readable index is available in llms.txt.
| Area | What is inside | Start here |
|---|---|---|
| 🤖 Plugin agents | Host packages for Claude Code, Codex, Gemini CLI, Antigravity CLI, and Cursor | plugins/README.md |
| 🖱️ Cursor IDE | Cursor plugin metadata, generated agents, and support skills | .cursor-plugin/plugin.json |
| 🐍 Cursor SDK | Python SDK launcher and generated prompts for automation | cursor-sdk/README.md |
| 🧩 Single-agent bundles | Manual per-host artifacts and README files | Agent Catalog |
| 🧱 Portable bundles | Runtime-neutral prompts, manifests, output contracts, and adapter expectations | portable/ |
| 🛠️ Source recipes | Maintainer-only source of truth for behavior, evals, actions, and diagrams | source/agents/ |
| 🔒 Guardrails | Safety, provenance, runtime, and documentation validation | docs/guardrails.md |
Current generated plugin package version: 2.0.0.
| Host | Best for | First move |
|---|---|---|
| Claude Code | Full plugin agents plus Claude-only helper agents | Read plugins/claude/endor-labs-agent-kit/README.md, then install endor-labs-agent-kit@endorlabs. |
| Codex | Skills plus optional bundled custom-agent TOML files | Read plugins/codex/endor-labs-agent-kit/README.md. |
| Gemini CLI | Extension with skills and preview subagents | Read plugins/gemini/endor-labs-agent-kit/README.md. |
| Antigravity CLI | Plugin with skills and subagents | Read plugins/antigravity/endor-labs-agent-kit/README.md. |
| Cursor IDE | Customer-facing Cursor plugin agents | Install from .cursor-plugin/, root agents/, root skills/, and assets/logo.svg. |
After installing any host package, run setup first:
Use the endor-agent-kit-setup skill to check Endor Agent Kit readiness. Do not run scans.
The plugin packages are the lowest-friction way to load Endor Labs workflows into Claude Code, Codex, Gemini CLI, Antigravity CLI, or Cursor. They package setup guidance and generated workflow agents/skills from the same source recipes as the manual catalog without injecting every recipe into the active model context.
Claude compatibility note: ai-plugins@endorlabs remains available for
existing Claude Code users and pinned installs. New users should prefer
endor-labs-agent-kit@endorlabs. Do not enable both Claude plugin ids in
one profile because they expose the same setup skill and agents. The
plugin does not auto-disable, uninstall, or edit Claude settings for
either id.
After installing a plugin, ask the host to use the endor-agent-kit-setup
skill first. Setup checks local readiness, guides endorctl authentication
and namespace selection, reports gh and toolchain gaps, and offers
host-specific self-checks before live Endor lookups.
npx claudepluginhub endorlabs/endor-labs-agent-kit --plugin ai-pluginsSet up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
Endor Labs workflow agents and setup for Claude Code.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Binary reverse engineering, malware analysis, firmware security, and software protection research for authorized security research, CTF competitions, and defensive security
AI-powered development tools for code review, research, design, and workflow automation.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows