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 skills add fatihkan/badi --skill pentest-orchestratorgit clone --depth 1 https://github.com/fatihkan/badiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fatihkan/badi/pentest-orchestrator)<a href="https://agentmods.dev/skills/fatihkan/badi/pentest-orchestrator"><img src="https://agentmods.dev/badge/skills/fatihkan/badi/pentest-orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fatihkan/badi/pentest-orchestrator"><img src="https://agentmods.dev/badge/skills/fatihkan/badi/pentest-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00000 | $0.01390 |
| Opus 5 | $0.00000 | $0.00695 |
| Sonnet 5 | $0.00000 | $0.00278 |
| Haiku 4.5 | $0.00000 | $0.00139 |
Grade A, and why
pentest-orchestrator 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 3d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pentest-orchestrator
The main orchestrator for an authorized penetration testing engagement. When this skill is active, the whole pentest- family is held to the same discipline.
What It Does
- At engagement start it asks for a scope declaration (IP ranges, domain names, URLs, cloud accounts, ROE)
- Applies OPSEC tagging to every command: QUIET / MODERATE / LOUD
- Evidence handling: timestamped log files + sanitized target names
- Hard refusal list: DoS, mass scanning, worms, persistent backdoors, false-flag, safety-of-life systems
- Coordinates the recon-to-report flow; routes to the appropriate pentest- sub-category
What It Does Not Do (Out of Scope)
- Live exploit execution (running SQL injection payloads, msfvenom payload generation, starting a C2 beacon) — use a dedicated pentest tool for these
- Commands without authorization — if scope has not been declared in advance, no command is composed for any target
- Unauthorized mass scanning — anything like
masscan 0.0.0.0/0is always refused - Self-propagating implants or backdoors
Session Initialization Protocol
At the start of every engagement, the following questions to the user are mandatory:
- Authorized scope (in-scope assets):
- IP ranges (CIDR)
- Domains and subdomains
- URL path restrictions
- Cloud account IDs / subscriptions
- Engagement type: external / internal / web-app / cloud / wireless / red-team / bug-bounty
- ROE (Rules of Engagement): forbidden techniques, working hours, contact info
- Proof of authorization: written permission / engagement letter / bug bounty program URL
Keep the answers in session memory and cross-check while composing every command. Out-of-scope target -> do not compose the command + redact.
Command Composing Rules
| Rule | Description |
|---|---|
| No action before explanation | Every command is explained first (what it does, what it connects to, what it returns) |
| Quietest first | TCP connect > SYN, passive DNS > zone transfer, banner > full-scan |
| Rate limit by default | timeout + parallel limit always on (to zero out DoS risk) |
| Evidence save | All output to a file: {tool}_{target-sanitized}_{YYYYMMDD-HHMMSS}.{ext} |
| No blind pipe | ` |
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.
- 3d ago First seen · 113 lines · 0 tokens per session scan A 14402b22277e
pentest-orchestrator is a skill published in the GitHub repository fatihkan/badi (7 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,390 tokens. 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 2026-09-06.
Other skills, from other repositories
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.