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/secrets-huntgit 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 | $0.00566 |
| Opus 5 | $0.00000 | $0.00283 |
| Sonnet 5 | $0.00000 | $0.00113 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
secrets-hunt 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `streaak/keyhacks` shows the canonical curl-one-liner per provider. What it actually says
/secrets-hunt
Find leaked API keys, tokens, and credentials — verified when possible.
Usage
/secrets-hunt --filesystem /path/to/project
/secrets-hunt --git https://github.com/target/repo
/secrets-hunt --js-bundle recon/target.com
/secrets-hunt --github-org acme-corp # needs GITHUB_TOKEN env
Scanners (best installed wins; the script runs whichever it finds)
| Scanner | Strength |
|---|---|
trufflehog |
Verifies live keys against the issuer API (AWS/Slack/Stripe/GH/...) |
noseyparker |
Fast on massive git histories with low false-positive rate |
gitleaks |
Opinionated rule pack — solid default for repos |
If none are installed the script still runs a regex fallback over the target so
something useful comes out — but you should install at least trufflehog
(brew install trufflehog) for the verified-only output.
Why this is high-impact
- Leaked AWS / GCP / Slack / Twilio / OpenAI tokens are typically rated High to Critical ($1k–$10k+) on H1.
- Verified-only mode kills the noisy false positives that get reports closed.
- JS-bundle mode is the easiest win — companies regularly ship tokens in bundled frontend JavaScript.
Verifying the find
When a hit comes back, verify the key works the right way before submitting:
streaak/keyhacksshows the canonical curl-one-liner per provider.- Submit only verified, in-scope keys.
- Don't pivot off the key (no further actions on the cloud account beyond proving it works) — most programs treat that as out-of-scope.
Output
findings/secrets/<timestamp>/ containing:
trufflehog.jsonl— verified hits (high-confidence)noseyparker.jsonl— match groups across the historygitleaks.json— opinionated default-rule hitsregex_hits.txt— regex fallback (manual triage required)
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 · 54 lines · 0 tokens per session scan A 5f988d23bc7f
secrets-hunt is a command published in the GitHub repository Awarexone/Agentic-Bug-Hunter (4,651 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 566 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].
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.