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/spraygit 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 | $0.01579 |
| Opus 5 | $0.00000 | $0.00790 |
| Sonnet 5 | $0.00000 | $0.00316 |
| Haiku 4.5 | $0.00000 | $0.00158 |
Grade A, and why
spray 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.
| `http-form` | Custom login page (POST username/password) | Built-in Python + urllib | How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spray
Live credential spray against an authentication endpoint. The most dangerous tool in this plugin. Read the guards section before using.
Modes
| Mode | Use case | Engine |
|---|---|---|
http-form |
Custom login page (POST username/password) | Built-in Python + urllib |
oauth |
OAuth password grant (grant_type=password) |
Built-in Python + urllib |
o365 |
Microsoft 365 / Azure AD | trevorspray |
okta |
Okta SSO | trevorspray |
Usage
# HTTP form (simplest)
/spray https://target.com/login --mode http-form \
--users users.txt --passes ranked.txt
# HTTP form with CSRF token extraction
/spray https://target.com/login --mode http-form \
--users users.txt --passes ranked.txt \
--post-data "user={USER}&pass={PASS}&_token={CSRF}" \
--csrf-extract 'name="_token" value="([^"]+)"' \
--success-regex "Welcome" \
--fail-regex "Invalid credentials"
# OAuth password grant
/spray https://target.com/oauth/token --mode oauth \
--users users.txt --passes ranked.txt \
--oauth-client-id mobile-app \
--oauth-scope "openid profile"
# Microsoft 365 (TREVORspray)
/spray https://login.microsoftonline.com --mode o365 \
--users users.txt --passes ranked.txt
# Dry-run (pre-flight only, no real attempts)
/spray https://target.com/login --mode http-form \
--users users.txt --passes ranked.txt --dry-run
Hard guards (cannot be bypassed)
- Typed-hostname confirmation — Pre-flight prints the target hostname and requires you to type it back. Prevents spraying the wrong target.
- Lockout warning — Calculates per-user failed-attempt count from your
--passessize and warns if it exceeds typical lockout thresholds. - Audit log — Every attempt is appended to
recon/<host>/spray/attempts-<timestamp>.jsonl. Format:{ts, round, user, pwd_sha256_prefix, status_code, looks_like_success, duration_ms}. Passwords are never logged in plaintext — only their SHA-256 prefix. - Spray order —
pass[i] × all_usersper round (NOT brute-per-user). Each account sees at most 1 failed attempt per round.
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 · 145 lines · 0 tokens per session scan A 2428a35a27bf
spray 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 1,579 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.