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/scopegit 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 | $0.00962 |
| Opus 5 | $0.00000 | $0.00481 |
| Sonnet 5 | $0.00000 | $0.00192 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
scope 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- scope — 91% identical, 22 lines differ
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/scope
Verify an asset is in scope before hunting or submitting a finding.
Why This Matters
Out-of-scope reports are immediately closed. Testing out-of-scope assets can get you banned. Always check scope BEFORE the first request.
Real example: City of Vienna explicitly excludes /advuew/*. Submitting XSS on that path = instant close.
Usage
/scope api.target.com
/scope https://target.com/api/v2/users
/scope target-staging.company.com
/scope *.company.com
Deterministic Local Check
Use the local scope checker before sending traffic:
python3 tools/scope_checker.py https://api.target.com/v2/users \
--domain target.com \
--domain '*.target.com' \
--exclude-domain staging.target.com
Filter a discovered URL list:
python3 tools/scope_checker.py \
--domain target.com \
--domain '*.target.com' \
--exclude-domain staging.target.com \
--input-file recon/target.com/urls/all.txt \
--output recon/target.com/urls/in_scope.txt
Scope Check Process
Step 1: Read In-Scope List
Go to the program page and extract:
In-scope:
- *.target.com
- target.com
- api.target.com
- mobile.target.com (iOS + Android apps)
Out-of-scope:
- staging.target.com (explicitly excluded)
- target.com/help/* (documentation only)
- partners.target.com (third-party managed)
Step 2: Asset Ownership Check
Verify the asset is actually owned by the target company (not a third party):
# WHOIS
whois api.target.com | grep -iE "registrant|admin|tech|org"
# DNS — is it CNAME to a third party?
dig +short api.target.com CNAME
# If CNAME to salesforce.com, zendesk.com, etc. → not in scope
# Check if it's a known third-party service:
# intercom.io, freshdesk.com, zendesk.com, hubspot.com, etc.
Step 3: Wildcard Interpretation
| Scope Pattern | Covers | Does NOT Cover |
|---|---|---|
*.target.com |
api.target.com, app.target.com |
target.com itself |
target.com |
target.com only |
api.target.com |
*.target.com + target.com |
Both | Sub-subdomains like a.api.target.com (depends on program) |
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 · 129 lines · 0 tokens per session scan A 9ab9f37e2913
scope 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 962 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].
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.