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/s0ld13rr/pentestcode/webappnpx skills add s0ld13rr/pentestcode --skill webappgit clone --depth 1 https://github.com/s0ld13rr/pentestcodeWhat 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 | $0.00078 | $0.00673 |
| Opus 5 | $0.00039 | $0.00336 |
| Sonnet 5 | $0.00016 | $0.00135 |
| Haiku 4.5 | $0.00008 | $0.00067 |
Grade A, and why
playbook-webapp 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web App Pentest — methodology + skill router
This is the ORDER of operations and the map to the deep skills. Each vuln CLASS has a dedicated web-<class> skill with exact payloads + detect→exploit→PROVE — load the one matching the surface; don't test from this index.
1. Recon + active scan FIRST
Fingerprint stack+version (whatweb/httpx, headers), CMS (wpscan/etc.), APIs (/swagger, /graphql, /.well-known). Then a content-matched nuclei -u <t> pass BEFORE exhaustive dir-fuzz (framework-runtime RCEs don't appear as routes) → nuclei_parse. Version + a known CVE → fetch & vet a public PoC (shared exploitation methodology).
2. Map (hidden surface, AFTER the scan)
ffuf/gobuster (→ gobuster_parse), vhosts (ffuf -H Host:FUZZ), params (arjun), auth endpoints (login/register/reset/OAuth), API routes. Review client-side JS for endpoints/secrets.
3. Test by class → load the matching skill
| Signal / surface | Load |
|---|---|
| param → DB query, SQL error/differential | web-sqli |
| input renders in a server template ({{7*7}}) | web-ssti |
| server fetches a URL you control (webhook/proxy/import) | web-ssrf |
file param / download / ../ reflection |
web-lfi-traversal |
| file upload sink | web-upload-rce |
| XML/SOAP/SAML/DOCX/SVG parsing | web-xxe |
| serialized blob (rO0/O:/VIEWSTATE/pickle) | web-deserialization |
| object IDs, roles, JWT, admin funcs | web-auth-bypass-idor |
| known framework+version CVE | shared exploitation methodology + searchsploit/nuclei |
Also-check (no dedicated skill yet): XSS (dalfox, xss_detect), command injection (;id/$(id)), CSRF, CORS/security-headers, crypto/secrets-in-JS, business-logic/race conditions. |
4. PROVE + Report
A finding is suspected until you reproduce concrete impact (dumped canary row / id / file bytes / cloud creds / cross-user data) — then add_vuln confirmed with the evidence. Never mark a host resolved/"safe" without a completed active scan. Report: reproduction steps + request/response evidence + CVSS + OWASP-WSTG mapping.
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 · 33 lines · 78 tokens per session scan A 3ae0659e1511
playbook-webapp is a skill published in the GitHub repository s0ld13rr/pentestcode (566 stars, last pushed 11d ago), licensed MIT. It adds 78 tokens to every session and 673 once invoked, about $0.0004 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
stripe-projects
Use after E2B sandbox/API access has been provisioned through Stripe Projects and the user needs to use the resulting E2B API key with the E2B CLI, JavaScript SDK, Python SDK, or Code Interpreter SDK.
greeting-user
Explains how to properly greet the user.
using-process-tool
Describes how to correctly use 'process' tool.
test-skill
test description.
documents
Create, read, edit, review, comment on, sanitize, render, and validate Microsoft Word DOCX documents. Use whenever a DOCX or Word document is a primary input or deliverable, including reports, proposals, forms, templates, tracked revisions, comments, tables, images, headers, footers, and style-preserving edits.
Read, create, inspect, merge, split, rotate, encrypt, fill, and validate PDF files. Use when the user asks to work with a PDF or convert supported Markdown into a polished PDF in AstrBot.