Mantis Pipeline

by deonmenezes

Mantis Pipeline is an AI Engineering skill for Claude Code, published by deonmenezes in mantishack.

490 stars73 forkson deonmenezes/mantishackAdded 2026/08/26Repository updated 2026/08/11

View source on GitHub Download repo ZIP

agent-harnessai-agentsautonomous-agentsbug-bountyclaude-codemantismcpoffensive-securitysecurity

Install in seconds

Install Mantis Pipeline

Copy Mantis Pipeline into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/deonmenezes/mantishack/tree/main/.codex/skills/mantis-pipeline ~/.claude/skills/mantis-pipeline

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/deonmenezes/mantishack.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .codex/skills/mantis-pipeline/SKILL.md in deonmenezes/mantishack
Installs to: ~/.claude/skills/mantis-pipeline
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Mantis Pipeline does

Mantis Pipeline runs an authorized, staged vulnerability-discovery workflow from recon through validation, verification, chaining, and reporting. Use it to coordinate tools, agents, and evidence handling across the finding lifecycle.

Mantis Pipeline is cataloged under AI Engineering on DirSkills. Mantis Pipeline comes from a repository tagged agent-harness, ai-agents, autonomous-agents, bug-bounty and claude-code.

Documentation

README

Excerpt

Mantis runs a staged detect-then-validate pipeline. The core bet: detection is commodity, validation precision is the product -- "what survives attacker-simulation is real." Detect is generous (high recall, no self-censoring); Validate is ruthless (kill false positives with cited roadblocks).

Establish scope and authorization FIRST. Work only on targets the user owns or is explicitly authorized to test. If authorization for active/exploit testing is unclear, restrict the run to read-only static analysis until scope is established. Never do destructive, persistence, exfiltration, DoS, or stealth actions.

Pipeline, stage -> subagent (spawn_agent agent_type) -> tools:

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Mantis Pipeline

What else does deonmenezes publish alongside Mantis Pipeline?
Mantis Pipeline is one of 25 skills that DirSkills catalogs from deonmenezes/mantishack, the repository it ships in. Its siblings there include Canary Tripwire Response, Code Breaking Changes and Code Review. Each one is a separate skill with its own page in this directory, installs the same way Mantis Pipeline does, and is maintained by deonmenezes in that same repository. The rest of the collection is listed on the deonmenezes/mantishack page.
How does Mantis Pipeline compare to other AI Engineering skills?
Mantis Pipeline ranks #2192 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Mantis Pipeline against them. Open each page to compare what they document and how they install.