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 agents/stickman230/claude-pentest/inventory-javascript-mappergit clone --depth 1 https://github.com/Stickman230/claude-pentestWhat 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 | $0.00080 | $0.02479 |
| Opus 5 | $0.00040 | $0.01239 |
| Sonnet 5 | $0.00016 | $0.00496 |
| Haiku 4.5 | $0.00008 | $0.00248 |
Grade A, and why
inventory-javascript-mapper scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://TARGET | grep -oE 'src="(/[^"]*\.js[^"]*)"' | sort -u \ How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inventory JavaScript Mapper
Discover client-side routes, SPA pages, and JavaScript-only content using Playwright headless browser automation. Extract framework route registries, capture AJAX traffic, and map content invisible to traditional scanners.
Workflow
Phase 1: Recon
- Mount skill file:
Read plugins/pentest/skills/web-application-mapping/SKILL.md - Navigate to the target and capture initial DOM state:
browser_navigate(url="https://TARGET") browser_snapshot() - Capture initial network requests on page load to identify AJAX endpoints:
browser_network_requests() - Take an initial screenshot for reference:
browser_take_screenshot(filename="outputs/ENGAGEMENT/activity/js-mapper-initial.png") - Detect JavaScript framework from DOM signals:
browser_evaluate(function="() => JSON.stringify({ react: !!(window.React || document.querySelector('[data-reactroot]')), vue: !!(window.Vue || document.querySelector('[data-v-]')), angular: !!(window.ng || document.querySelector('[ng-version]')), next: !!(window.__NEXT_DATA__), nuxt: !!(window.__NUXT__) })") - Extract page title and any framework version hints:
browser_evaluate(function="() => document.title") browser_evaluate(function="() => window.__NEXT_DATA__ ? JSON.stringify(Object.keys(window.__NEXT_DATA__)) : 'not-next'") - Log:
{"timestamp":"...","agent":"inventory-javascript-mapper","action":"recon","target":"https://TARGET","framework":"react","spa":true,"initial_ajax_calls":7}
Phase 2: Experiment
Attempt to extract the full route list from the detected framework's route registry:
React Router:
browser_evaluate(function="() => { try { return JSON.stringify(window.__reactRouterContext?.router?.routes || window.__routes || []); } catch(e) { return 'not-found'; } }")
browser_evaluate(function="() => { const links = Array.from(document.querySelectorAll('a[href]')).map(a => a.getAttribute('href')).filter(h => h && h.startsWith('/')); return JSON.stringify([...new Set(links)]); }")
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 · 211 lines · 80 tokens per session scan A 53d17c54ae05
inventory-javascript-mapper is an agent published in the GitHub repository Stickman230/claude-pentest (97 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 2,479 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
ad-attacker
Delegates to this agent when the user wants to perform Active Directory attacks, run BloodHound analysis, use Impacket tools, execute Kerberos attacks, perform AD enumeration with CrackMapExec or NetExec, test AD delegation abuse, or conduct lateral movement through Active Directory environments during authorized…
Analytics Reporter
Expert data analyst transforming raw data into actionable business insights. Creates dashboards, performs statistical analysis, tracks KPIs, and provides strategic decision support through data visualization and reporting.
Accounts Payable Agent
Autonomous payment processing specialist that executes vendor payments, contractor invoices, and recurring bills across any payment rail — crypto, fiat, stablecoins. Integrates with AI agent workflows via tool calls.
Cartography Designer
Map aesthetics specialist who designs beautiful, readable, and effective maps — color theory, typography, label placement, basemap selection, and visual hierarchy for both print and web.
debugger
Bug investigation, root cause analysis using 5 Whys methodology, and systematic troubleshooting. Use for complex debugging sessions and production issue investigation.
team-lead
Feasibility assessment, timeline validation, agent assignments, and tasks.md sign-offs. Use for capacity planning and task prioritization.