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/elementalsouls/claude-bughunter/triagegit clone --depth 1 https://github.com/elementalsouls/Claude-BugHunterWhat 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 | $0.00045 | $0.00837 |
| Opus 5 | $0.00023 | $0.00418 |
| Sonnet 5 | $0.00009 | $0.00167 |
| Haiku 4.5 | $0.00005 | $0.00084 |
Grade A, and why
triage 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 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.
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/triage
Quick triage to decide: submit or kill?
When to Use
Use this before spending time writing a full report. If triage passes, run /validate for the full 4-gate check, then /report.
Usage
/triage
Describe the finding in one sentence. Example:
- "I can read other users' orders by changing user_id in /api/orders/{id}"
- "The /api/export endpoint returns 200 with data even with no auth header"
- "I found X-Forwarded-Host is reflected in the password reset email"
The 7 Questions (Fast Version)
Answer YES or NO to each. First NO = kill it immediately.
Q1: Can I demonstrate this with a real HTTP request RIGHT NOW?
YES: I have the request/response already
NO: I need to look at more code first → KILL
Q2: Is this impact type accepted by the program?
YES: Bug class is on their accepted list
NO: They explicitly exclude this type → KILL
Q3: Is the vulnerable asset owned by and in scope for the program?
YES: Domain confirmed in-scope, not third-party
NO: Third-party service or excluded domain → KILL
Q4: Does this work without admin/privileged access?
YES: Regular user account is enough
NO: Requires admin → KILL (99% of programs)
Q5: Is this NOT already known/disclosed/documented behavior?
YES: Not in changelogs, not in disclosed reports
NO: It's documented as intended → KILL
Q6: Can I prove impact beyond "technically possible"?
YES: I have actual data in the response / action completed
NO: I only have a 200 status or error message → DOWNGRADE
Q7: Is this NOT on the never-submit list?
YES: It's a real bug class
NO: Missing headers, self-XSS, open redirect alone, etc. → KILL or CHAIN
Fast Kill Checklist
Kill immediately if ANY of these are true:
[ ] "Admin can do X" = not a bug
[ ] "Could theoretically lead to..." = no PoC = not a bug
[ ] Bug requires 3+ preconditions simultaneously
[ ] Finding is a missing header, missing flag, missing DMARC
[ ] SSRF with DNS callback only, no data returned
[ ] Open redirect with no OAuth chain or ATO path
[ ] Self-XSS (only affects your own account)
[ ] Introspection only (no IDOR, no auth bypass shown)
[ ] Rate limit on login/contact/search (Cloudflare covers it)
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 · 97 lines · 0 tokens per session scan A c319f357f434
triage is a command published in the GitHub repository elementalsouls/Claude-BugHunter (3,853 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 837 once invoked, about $0.0002 per session on Opus 5. 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
bypass-403
Probe a 403/401 endpoint with the most-paid bypass tricks (header injection, path encoding, method swap, WAF fingerprint, vendor-specific). Wraps byp4xx when installed; otherwise runs a built-in matrix of 38+ techniques. Usage: /bypass-403 | /bypass-403 -l.
spray
Password spray with hard guards — typed-hostname confirmation, lockout warning, audit log. Modes: http-form (custom login page), oauth (password grant), o365 + okta (via TREVORspray). Default delay 30min/round + 60s jitter. Usage /spray --mode --users --passes.
web3-audit
Smart contract security audit — runs through 10 bug class checklist (accounting desync, access control, incomplete path, off-by-one, oracle errors, ERC4626, reentrancy, flash loan, signature replay, proxy/upgrade). Applies pre-dive kill signals first. Generates Foundry PoC template for confirmed findings. Usage…
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].
recon
Run the full recon pipeline by invoking tools/reconengine.sh — subdomain enum (subfinder + amass + crt.sh + wayback), httpx live host probing with tech detection, nmap port scan, gau URL collection, JS analysis, ffuf directory fuzzing, parameter discovery, config exposure check, CI/CD workflow scan. Outputs to recon/…
report
Write a submission-ready bug bounty report. Generates H1/Bugcrowd/Intigriti/Immunefi format with CVSS 3.1 score, proof of concept, impact statement, and remediation. Run /validate first. Usage: /report.