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/strategic-automation/violin/pentestnpx skills add Strategic-Automation/violin --skill pentestgit clone --depth 1 https://github.com/Strategic-Automation/violinWhat 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 | $0.00017 | $0.01754 |
| Opus 5 | $0.00009 | $0.00877 |
| Sonnet 5 | $0.00003 | $0.00351 |
| Haiku 4.5 | $0.00002 | $0.00175 |
Grade A, and why
pentest scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pentest Orchestrator
The authoritative engagement lifecycle and skill router. It does not contain vulnerability payloads or tool matrices: load the matched phase playbook and specialist skill on demand.
Non-Negotiable Contract
- Test only an approved scope. Target-touching work uses
violin_execorviolin_exec_burst; host-local preparation may useterminal. - Maintain exactly one active
[~]PTT task. Keep structured hypotheses, evidence, coverage, and phase state under$ENG_DIR. - Store raw proof only under
$ENG_DIR/evidence/<phase>/; never store secrets or evidence inskills/or$ENG_DIR/state/. - Do not close an engagement without
reporting/report.mdandretrospective/retrospective.md.
Load on Demand
| Need | Read |
|---|---|
| Scope, stop conditions, safety | references/shared-safety.md and .hermes.md |
| Evidence, confidence, CVSS | references/standards.md and references/evidence-and-verification-discipline.md |
| Exhaustive coverage matrix | references/exhaustive-coverage.md |
| Pre-REPORTING common-class sweep | references/coverage-closeout.md |
| Methodology gates (close-gate checklist) | state/methodology-gates.yaml (dispositioned in VULN_RESEARCH) |
| Repeated failure or stalled research | references/anti-stuck.md |
| Platform, delegation, tool fallback | references/platform-delegation.md |
| CVE and public vulnerability research | references/cve-apis.md |
Keep tool summaries to five lines or fewer: result, evidence path, and next validated action. Redact credentials and tokens in chat and state artifacts.
Output Budget
Keep batch summaries to 3-5 bullets. Save raw output strictly under
$ENG_DIR/evidence/<phase>/; do not paste full scanner output into chat, quote only decisive lines. Never summarize away evidence needed for validation: preserve full output, command, timestamp, and artifact path in the saved file.
State & Context Continuity
On every phase change, write $ENG_DIR/state/phase-summary.md and update
$ENG_DIR/state/checkpoint.json (phase_current, open_items). If context is
at risk of compression, tell the user: "Continue in the current session; I will
resume from $ENG_DIR/state/ files." Re-read $ENG_DIR/state/checkpoint.json,
$ENG_DIR/state/ptt.md, and $ENG_DIR/state/phase-summary.md before the next
action. Do not reconstruct tested state from memory after compression.
What ships with it
43 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- playbooks/anti-automation.md 7.6 KB
- playbooks/exploitation.md 9.5 KB
- playbooks/post-exploitation.md 4.4 KB
- playbooks/recon.md 16 KB
- playbooks/reporting.md 12 KB
- playbooks/scoping.md 12 KB
- playbooks/supply-chain.md 7.5 KB
- playbooks/tools.md 8.6 KB
- playbooks/vuln-research.md 13 KB
- references/anti-stuck.md 2.0 KB
- references/api-testing.md 3.5 KB
- references/coverage-closeout.md 2.4 KB
- references/cve-apis.md 6.2 KB
- references/evidence-and-verification-discipline.md 8.8 KB
- references/exhaustive-coverage.md 7.1 KB
- references/exploitation-patterns.md 2.7 KB
- references/flags-mode.md 2.2 KB
- references/kali-parrot-paths.md 3.4 KB
- references/methodology.md 11 KB
- references/platform-delegation.md 3.7 KB
- references/pty-safe-delivery.md 1.3 KB
- references/real-world-coverage-matrix-template.yaml 3.8 KB
- references/recon-methodology.md 2.1 KB
- references/retrospective.md 3.5 KB
- references/shared-safety.md 2.6 KB
- references/standards.md 14 KB
- references/tool-catalog.md 12 KB
- references/tool-discovery.md 6.8 KB
- templates/checkpoint.json 371 B
- templates/coverage-matrix.yaml 1.2 KB
- templates/cvss4-crosswalk.md 2.4 KB
- templates/detection-engineering.md 3.2 KB
- templates/finding-FIND-NNN.md 1.1 KB
- templates/flag-capture-register.md 2.5 KB
- templates/hypothesis-board.md 3.9 KB
- templates/methodology-gates.md 3.5 KB
- templates/methodology-gates.yaml 1.8 KB
- templates/ptt.md 4.5 KB
- templates/report-template.md 5.6 KB
- templates/scope-template.yaml 4.6 KB
- templates/shell_ctrl.py 2.4 KB runs code
- templates/transparency-boilerplate.md 868 B
- templates/verification-receipt.yaml 775 B
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.
- yesterday First seen · 146 lines · 17 tokens per session scan A eafcb0b58392
pentest is a skill published in the GitHub repository Strategic-Automation/violin (84 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 1,754 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
performing-jwt-none-algorithm-attack
Execute and test the JWT none algorithm attack to bypass signature verification by manipulating the alg header field in JSON Web Tokens.
Web Application Security Testing
OWASP Top 10 testing, injection vulnerability detection, API security assessment, authentication testing, and web vulnerability reporting for authorized assessments.
kali-pentest-zh
通过 SSH 或 Docker 使用 Kali Linux CLI 工具执行授权渗透测试。 覆盖：信息收集、漏洞分析、嗅探与欺骗、Web/API 渗透、漏洞利用、密码攻击、无线、云原生安全、RFID/NFC、VoIP/ICS、逆向工程、取证分析、后渗透/C2、报告生成。.
kali-pentest
Execute authorized penetration testing via Kali Linux CLI tools over SSH or Docker. Covers: information gathering, vulnerability analysis, sniffing & spoofing, web/API testing, exploitation, password attacks, wireless, cloud-native security, RFID/NFC, VoIP/ICS, reverse engineering, forensics, post-exploitation/C2, and…
managed-pentesting-with-strix
Run a managed pentest of a web app or API through the app.strix.ai REST API — no local Docker, LLM key, or install needed. Create an API token, register domain/repository assets, launch and poll scans, triage vulnerabilities, export SARIF, download PDF/DOCX pentest reports for SOC 2 and other compliance evidence…
007
Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.