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/sastgit 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 | $0.00472 |
| Opus 5 | $0.00000 | $0.00236 |
| Sonnet 5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
sast 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 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.
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.
What it actually says
/sast
Recon downloads JS bundles and (sometimes) leaked source, but nothing runs a real static analyzer over it — the skills' grep patterns get eyeballed by hand. This drives Semgrep across that source and normalizes every hit into this toolkit's states so findings drop straight into the validation gate.
Usage
/sast recon/target.com/js/ # default security packs
/sast app/ --config p/xss,p/jwt
/sast app.js --json
Run directly:
tools/sast_scan.py recon/target.com/js/
Rulesets
Default packs (Semgrep Registry): p/security-audit, p/secrets, p/xss,
p/sql-injection, p/command-injection. Override with --config. Registered
in tools/external_arsenal.sh as semgrep|sast; if Semgrep isn't installed the
command prints the install hint and exits cleanly.
Severity mapping
| Semgrep | Toolkit | Notes |
|---|---|---|
ERROR |
HIGH | |
WARNING |
MEDIUM | bumped to HIGH for sql-injection / rce / ssrf / secret / xxe / path-traversal rules |
INFO |
INFORMATIONAL | not a vulnerability on its own |
Confidence — read this
Every SAST hit is tagged POSSIBLE, never CONFIRMED. Static analysis is a
lead, not proof: a flagged sink still needs a live request that demonstrates
impact before it goes in a report. /validate enforces this — no runtime PoC,
no submission. Use /sast to point /hunt at the right lines fast, not to file
findings directly.
Chain
/recon → JS/source pulled → /sast → ranked sink list → /hunt the HIGH
sinks → /validate with a real PoC → /report.
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 · 53 lines · 0 tokens per session scan A 1af4d32f2886
sast 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 472 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.