Updated 7mo ago
by d0gesec
pownie
The agent harness for offsec. It's a plugin for Claude Code packed with skills, hooks, memory system that works best for using Claude Code to achieve autonomous pentest/ctf
24 GitHub stars (24)
Steady at 24 stars — no new stars in the 16 days since Sep 30.
- 4 skills (4 skills found in its SKILL.md files)
- 4 forks (4 forks)
- 7mo ago last update (Last updated 7mo ago)
Install
Skills CLI
npx skills add d0gesec/pownie
Asks which skills and agents to install. Just one: npx skills add d0gesec/pownie --skill offsec-debrief — add -g for every project.
Claude Code
git clone https://github.com/d0gesec/powniecp -r "pownie/skills/offsec-debrief" ~/.claude/skills/
Copies the offsec-debrief skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add d0gesec/pownie
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
offsec-debrief
Post-challenge debrief — generates writeup with structured failure analysis. Outputs to writeup/ directory and updates MEMORY.md with key lessons.
skills/offsec-debrief/SKILL.md on GitHub (opens in a new tab) -
offsec-intel-graph
Neo4j graph database for offensive security intel. Model writes Cypher directly via MCP tools — no scripts, no wrappers.
skills/offsec-intel-graph/SKILL.md on GitHub (opens in a new tab) -
offsec-lead
Orchestrator agent for iterative-deepening multi-agent coordination. Manages task trees, spawns focused teammates, evaluates findings, and deepens research until evidence supports exploitation.
skills/offsec-lead/SKILL.md on GitHub (opens in a new tab) -
strategy-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
skills/strategy-compact/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.