Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/jessefmoore/offensive-claude-code/pentesternpx skills add jessefmoore/offensive-claude-code --skill pentestergit clone --depth 1 https://github.com/jessefmoore/offensive-claude-codeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00090 | $0.01537 |
| Opus 5 | $0.00045 | $0.00768 |
| Sonnet 5 | $0.00018 | $0.00307 |
| Haiku 4.5 | $0.00009 | $0.00154 |
Grade A, and why
pentester scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pentester — Engagement Orchestration
This skill is the entry point that makes the rest of the config work together. It does not add
new techniques; it sequences the ones already in kb/, skills/, skills/scripts/, and
agents/ into a repeatable analyze → decide → act → capture → re-assess loop.
When to invoke
- Start of any engagement, HackSmarter lab, or HTB box ("start a pentest against X", "new
engagement", "I'm doing HTB ",
/pentester). - Mid-engagement when you want the next move decided ("what's next?", "I'm stuck", "here's the output, re-assess").
Persona routing (pick one, per CLAUDE.md)
| Context | Persona | Skill to load | Phase files |
|---|---|---|---|
| HackSmarter lab / real internal engagement | Internal Pentester (OCD AD mindmap) | skills/active-directory-attack (+ skills/netexec) |
kb/phases/0–5 |
| Hack The Box machine | HTB Operator (0xdf) | skills/htb |
nmap → service enum → foothold → privesc |
The loop (run this every turn)
- Orient. Read
kb/INDEX.md; map the current signal/finding to the exact technique file. Don't scan blindly, don't invent commands when the KB has them. - Load the phase runbook. Open
kb/phases/<N>-<phase>.mdfor the current phase — it is the ordered "what to run next" list. (HTB: follow the enum→foothold→privesc flow inskills/htb.) - Load the domain skill for depth + OPSEC (
skills/netexec,skills/web-pentest,skills/privesc-linux, etc.). - Execute. Prefer existing helpers in
skills/scripts/(e.g.ssh_cmd.pyto pivot,nxc_kerberos_wrapper.py,ntds_diff.py); use exact syntax fromkb/<domain>/andkb/payloads/. Try--local-authalongside domain auth on Windows. - Validate. Confirm exploitability before claiming a finding. No proof = not a finding.
- Capture immediately. The moment a finding lands (creds, shell, privesc, lateral move, Kerberos abuse, ADCS, DCSync, sensitive data), invoke the right report-writer — don't batch.
- Re-assess. State current state + prioritized next steps; loop back to step 1.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 104 lines · 90 tokens per session scan A 9e02a1511a48
pentester is a skill published in the GitHub repository jessefmoore/offensive-claude-code (2 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 1,537 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…