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/bypass-403git 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 | $0.01470 |
| Opus 5 | $0.00000 | $0.00735 |
| Sonnet 5 | $0.00000 | $0.00294 |
| Haiku 4.5 | $0.00000 | $0.00147 |
Grade A, and why
bypass-403 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
built-in fallback runs the same set with `curl`. How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/bypass-403
Try to bypass an HTTP 403/401 response with header injection, path encoding, and method tampering — the standard battery from disclosed reports.
Usage
/bypass-403 https://target.com/admin
/bypass-403 -l recon/target.com/live/status_403.txt
What it tries
| Class | Examples |
|---|---|
| IP spoofing headers | X-Forwarded-For: 127.0.0.1, True-Client-IP, CF-Connecting-IP, X-Originating-IP, X-ProxyUser-Ip, Client-IP, Forwarded, X-Remote-Addr, X-Remote-IP, Via, X-HTTP-Method-Override |
| Path tricks | /%2e/, /%252e/, /.xxx, /xxx/, /xxx;/, /xxx..;/, /xxx%20, /xxx%09, //xxx, /./xxx |
| Suffix tricks | /xxx.json, /xxx.html, /xxx.css, /xxx# |
| Method tampering | POST, PUT, PATCH, TRACE on a GET-only endpoint |
| Content-Type confusion | application/json POST, multipart/form-data POST, dual Content-Type header trick |
| Vendor-specific | Cloudflare (TE + X-Forwarded-Host), AWS WAF (/**/ comment split), Imperva (%c0%2e unicode), F5 (double-slash path) |
| WAF fingerprint | Auto-detect via response headers/cookies (cf-ray → Cloudflare, x-amzn → AWS, TS cookie → F5, incap_ses → Imperva) |
When byp4xx (lobuhi/byp4xx) is installed it is used directly; otherwise the
built-in fallback runs the same set with curl.
WAF Fingerprinting
The script auto-detects WAF vendor from response headers and cookies, then applies vendor-specific tricks automatically. Uses wafw00f when installed; falls back to header/cookie signature match.
Fingerprint saved to findings/bypass/<ts>/waf_fingerprint.txt.
Payload Encoding (separate tool)
For payload-level bypass (SQLi/XSS keyword blocked by WAF):
tools/waf_encoder.py "' OR 1=1--" --class sqli
tools/waf_encoder.py "<script>alert(1)</script>" --class xss
tools/waf_encoder.py "<payload>" --layers 3 # triple URL-encode
tools/waf_encoder.py "<payload>" --json # machine-readable output
Generates 20-40 variants: URL encoding (1-3 layers), unicode escape, HTML entity, SQL comment injection, MySQL version comment, case mixing, operator substitution, base64 XSS wrappers, null byte insertion.
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 · 108 lines · 0 tokens per session scan A c7c2ff93fc46
bypass-403 is a command published in the GitHub repository Awarexone/Agentic-Bug-Hunter (4,651 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,470 tokens. 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 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].
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.
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.