Skills for Real Engineers. Straight from my .agents directory.
pentest-playbook
Agent skill fromuphiago/recon-skills
7-phase pentest pipeline from passive recon to exploitation.
How to install pentest-playbook
npx skills add uphiago/recon-skills# or add only this skill to Claude Code: copy the folder
meta/pentest-playbook/
# into
~/.claude/skills/pentest-playbook/ (all projects)
.claude/skills/pentest-playbook/ (one project)
1# Pentest Playbook Skill237-phase master pentest pipeline covering the full lifecycle from passive reconnaissance to exploitation and reporting. Distilled from 100+ targets across government, healthtech, fintech, e-commerce, ISP, and SMB sectors. This is the "meta-playbook" — it tells you what to do at each stage of an engagement and which skills to load for each phase.45## When to Use67- Starting a new pentest engagement with an unknown target.8- You need the canonical workflow for any type of target.9- After surface recon — this playbook tells you what to do next.10- Training — understand the full lifecycle of a professional pentest.1112## Prerequisites1314- Explicit authorization, target boundaries, and rate limits for the target.15- Tooling: `curl`, `httpx`, `jq`, `masscan`, `mysql`, `nmap`, `proxychains`, `rustscan`, `subfinder`.16- A writable evidence directory: `export OUTPUT_DIR="${OUTPUT_DIR:-./output}" && mkdir -p "$OUTPUT_DIR"`.17- For any state-changing step (writes, uploads, credential attempts), obtain explicit confirmation immediately before the command.1819## How to Run2021```bash22# Set once per engagement; every step below uses these.23TARGET="example.com" # or the engagement target24export OUTPUT_DIR="${OUTPUT_DIR:-./output}"2526# 1. Subdomain enumeration27subfinder -d $TARGET -silent | tee subs.txt28curl --max-time 30 --connect-timeout 10 -s "https://crt.sh/?q=%.$TARGET&output=json" | jq -r '.[].name_value' >> subs.txt2930# 2. Tech stack detection via response headers31…
Excerpt shown under the repository's MIT license.
More skills in recon-skills
Similar skill repositories
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
The open-source app everyone uses to manage agents at work
The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.
