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

24Stars on the repository

5Mods indexed here, across every type

5mo agoLast push, which is what freshness is scored on

MITLicence, which decides whether bodies are shown

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 4 mods

offsec-debrief

01

Skill Claude CodeCodex

Part of pownie

Post-challenge debrief — generates writeup with structured failure analysis. Outputs to writeup/ directory and updates MEMORY.md with key lessons.

24 5mo ago A 33 tokens original MIT

offsec-intel-graph

02

Skill Claude CodeCodex

Part of pownie

Neo4j graph database for offensive security intel. Model writes Cypher directly via MCP tools — no scripts, no wrappers.

24 5mo ago A 32 tokens original MIT

offsec-lead

03

Skill Claude CodeCodex

Part of pownie

Orchestrator agent for iterative-deepening multi-agent coordination. Manages task trees, spawns focused teammates, evaluates findings, and deepens research until evidence supports exploitation.

24 5mo ago A 40 tokens original MIT

strategy-compact

04

Skill Claude CodeCodex

Part of pownie

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

24 5mo ago A 26 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages:

1 more from d0gesec/pownie →