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 commands/awarexone/agentic-bug-hunter/domxssgit clone --depth 1 https://github.com/Awarexone/Agentic-Bug-HunterWhat 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 | $0.00000 | $0.00617 |
| Opus 5 | $0.00000 | $0.00309 |
| Sonnet 5 | $0.00000 | $0.00123 |
| Haiku 4.5 | $0.00000 | $0.00062 |
Grade A, and why
domxss 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/domxss
Reflected-XSS scanners see a payload echoed back in HTML but can't tell whether
it ran — CSP, framework auto-escaping, or a sink that never reaches
eval/innerHTML all silently kill it. This drives headless Chromium, fires a
uniquely-tagged payload through each parameter and the URL fragment, and only
reports a finding when the browser executes the canary. That's the difference
between "reflected, maybe" and a report-ready [CONFIRMED] DOM XSS.
Usage
/domxss "https://app.target.com/search?q=test"
/domxss "https://app.target.com/#name=x&redirect=y" --params name,redirect
/domxss "https://app.target.com/?q=1" --shot shots/domxss.png --json
Run directly:
tools/dom_xss_harness.py "https://app.target.com/search?q=test"
Requires
Playwright (a new dependency, registered in tools/external_arsenal.sh):
pip install playwright && playwright install chromium
If it isn't installed the command prints this hint and exits cleanly — the rest of the toolkit is unaffected.
How it decides
| Verdict | Meaning |
|---|---|
[CONFIRMED] |
the payload's unique canary executed in-browser — fired via alert/prompt/confirm, a hooked window.__cbbx sink, or the console. JS ran. |
[POSSIBLE] |
the canary is reflected into the DOM but did not execute (likely CSP/escaping). Worth a manual look, not a finding on its own. |
Injection points: every ?query parameter and every #fragment key
(fragment-based DOM XSS never reaches the server, so server-side scanners miss
it entirely). Add more with --params.
Why this matters
DOM XSS, client-side prototype pollution, and PostMessage bugs need a real DOM —
this is the harness that lets the agent confirm them instead of guessing.
A [CONFIRMED] hit passes /validate on its own because execution is proven;
--shot captures the screenshot for /report.
Chain
/recon → JS/param discovery → /domxss "<url>" --params <candidates> →
[CONFIRMED] → /report with the screenshot. Pairs with /sast (find the sink
in source) → /domxss (prove it fires).
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 · 62 lines · 0 tokens per session scan A 6ff11a298ec1
domxss is a command published in the GitHub repository Awarexone/Agentic-Bug-Hunter (4,684 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 617 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 2026-08-30.
Other commands, from other repositories
recon
Run full recon pipeline on a target — subdomain enum (Chaos API + subfinder), live host discovery (dnsx + httpx), URL crawl (katana + waybackurls + gau), gf pattern classification, nuclei scan. Outputs to recon/ / directory. Usage: /recon target.com.
hunt
Active vulnerability hunting. Two-track dispatcher — asks Red Team vs WAPT, hands off to hunt-dispatch skill and sibling commands. Usage: /hunt target.com | /hunt .target.com | /hunt targets.txt [--vuln-class X] [--source-code P] [--chrome].
token-scan
Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP lock bypass, authority retention, bonding curve exploits, fake renounce, sandwich amplification). Manual 8-class grep audit (with an optional automated scanner if present). Usage: /token-scan [--chain solana].
autopilot
Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo].
triage
Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage.
validate
Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate.