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/validategit 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 | $0.00041 | $0.00991 |
| Opus 5 | $0.00020 | $0.00495 |
| Sonnet 5 | $0.00008 | $0.00198 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
validate 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/validate
Run full validation on the current finding before writing a report.
What This Does
- Runs 7-Question Gate (one wrong answer = kill it)
- Checks against the always-rejected list
- Runs 4 pre-submission gates
- Outputs: PASS (write the report) or KILL (move on)
Usage
/validate
Describe the finding when prompted. Include:
- The endpoint
- The bug class
- What the PoC shows
- The target program
The 7-Question Gate
Answer each. ONE wrong answer = STOP.
Q1: Can I demonstrate this step-by-step RIGHT NOW?
Write this out:
1. Setup: I need [own account / another user's ID / no account]
2. Request: [exact HTTP method, URL, headers, body]
3. Result: Response shows [exact data / action completed]
4. Impact: Real consequence is [account takeover / PII exposed / money stolen]
5. Cost: Time: [X min], Capital: [$0 / $X]
If step 2 is "I need to look at the code more" → KILL IT.
Q2: Is the impact accepted by this program?
Check program scope page. Is your bug class listed? Is it excluded?
Q3: Is the vulnerable asset in scope?
Exact domain in scope? Not staging/dev? Not a third-party service?
Q4: Does it need admin or privileged access that an attacker can't get?
"Admin can do X" → KILL IT. "Regular user can do X that only admin should" → valid.
Q5: Is this known or documented behavior?
Search disclosed reports + changelog + API docs.
Q6: Can you prove impact beyond "technically possible"?
- XSS → actual cookie value in exfil request, not just alert()
- SSRF → response body from internal service, not just DNS callback
- IDOR → actual other-user's private data in response, not just 200 status
Q7: Is this on the never-submit list?
Missing headers, GraphQL introspection alone, clickjacking without PoC,
self-XSS, open redirect alone, SSRF DNS-only, logout CSRF, banner disclosure,
rate limit on non-critical forms, missing cookie flags alone...
If yes → KILL IT unless you have a chain.
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 · 135 lines · 0 tokens per session scan A 25e79666e957
validate is a command published in the GitHub repository elementalsouls/Claude-BugHunter (3,853 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 991 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.