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-engagementgit 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-engagement)<a href="https://agentmods.dev/skills/fatihkan/badi/pentest-engagement"><img src="https://agentmods.dev/badge/skills/fatihkan/badi/pentest-engagement/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-engagement"><img src="https://agentmods.dev/badge/skills/fatihkan/badi/pentest-engagement.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 | $0.00070 | $0.01111 |
| Opus 5 | $0.00035 | $0.00556 |
| Sonnet 5 | $0.00014 | $0.00222 |
| Haiku 4.5 | $0.00007 | $0.00111 |
Grade A, and why
pentest-engagement 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 4d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pentest-engagement
Produces planning + scoping + ROE documentation for an authorized penetration testing engagement.
Triggers
- "prepare a pentest plan"
- "draft the ROE"
- "scoping document"
- "engagement timeline"
- "MITRE ATT&CK matrix"
- "kickoff meeting agenda"
- "closeout report template"
Deliverables
- Scope Document (in-scope, out-of-scope, constraints)
- Rules of Engagement (ROE) (forbidden techniques, working hours, escalation path)
- Phased Timeline (kickoff -> recon -> exploit -> post-ex -> reporting -> closeout)
- MITRE ATT&CK Mapping (Tactic + Technique list per phase)
- Communication Plan (client contact, escalation contact, incident response)
- Acceptance Criteria (tests covered, reporting, deliverable list)
Scope Document Template
# Engagement Scope — <Client>
## In-Scope
- IP Ranges: 10.0.0.0/16, 192.168.50.0/24
- Domains: *.example.com, app.example.com
- Cloud Accounts: AWS 123456789012 (production us-east-1)
- Test Type: External / Internal / Web App / Cloud / Red Team
## Out-of-Scope
- Production DB direct query
- Email/Phishing a client employee
- DoS / stress testing
- 3rd party SaaS (Stripe, SendGrid, etc.)
## Restrictions
- Working hours: Weekdays 09:00-17:00 (TR)
- Aggressive scan: Only within a user-approved window
- Data exfil: None — evidence files only (max 1MB)
## Authorization
- Letter of authorization: <link>
- Client signature: <name, date>
- Pentest firm signature: <name, date>
Phased Plan Template (5 Phase)
| Phase | Duration | Activity | MITRE Tactic |
|---|---|---|---|
| 1. Recon | 1-2 days | OSINT, subdomain enum, port scan | TA0043 Reconnaissance |
| 2. Initial Access | 2-3 days | Web app exploit, phishing sim, AD attack | TA0001 Initial Access |
| 3. Post-Exploit | 3-4 days | Privesc, lateral, persistence, exfil sim | TA0004/TA0008/TA0003/TA0010 |
| 4. Detection | 1-2 days | SIEM/EDR coverage gap | TA0042 Resource Development (defensive) |
| 5. Report | 2-3 days | Finding writeup, CVSS, remediation, debrief | — |
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.
- 4d ago First seen · 129 lines · 70 tokens per session scan A 302e599b3624
pentest-engagement is a skill published in the GitHub repository fatihkan/badi (7 stars, last pushed 3d ago), licensed MIT. It adds 70 tokens to every session and 1,111 once invoked, about $0.0003 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 2026-09-06.
Other skills, from other repositories
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.
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.
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…
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.
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.