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.
git clone --depth 1 https://github.com/Mikacr1138/claude-bug-bountyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/mikacr1138/claude-bug-bounty/scope)<a href="https://agentmods.dev/commands/mikacr1138/claude-bug-bounty/scope"><img src="https://agentmods.dev/badge/commands/mikacr1138/claude-bug-bounty/scope/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/mikacr1138/claude-bug-bounty/scope"><img src="https://agentmods.dev/badge/commands/mikacr1138/claude-bug-bounty/scope.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.00836 |
| Opus 5 | $0.00000 | $0.00418 |
| Sonnet 5 | $0.00000 | $0.00167 |
| Haiku 4.5 | $0.00000 | $0.00084 |
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 8d 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.
This is a copy
91% identical to scope — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 107 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
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) |
Step 4: Path Exclusions
Some programs exclude specific paths on in-scope domains:
Domain: target.com (in scope)
But: target.com/terms, target.com/privacy, target.com/help/* = usually excluded
Check for:
- Wildcard exclusions: /admin/* excluded
- Path-specific exclusions: /api/v1/* excluded (use v2 only)
- Feature exclusions: "Do not test file upload feature"
Step 5: Staging / Dev Check
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.
- 8d ago First seen · 107 lines · 0 tokens per session scan A 16eafbb9c315
scope is a command published in the GitHub repository Mikacr1138/claude-bug-bounty (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 836 tokens. A static security scan graded it A with 0 findings. It is 91% identical to scope, differing in 22 lines, and is treated as a copy.
Other commands, from other repositories
sicario.controls
Generate or update docs/compliance/control-applicability.md.
sicario.assess
Assess the repository against SicarioSpec guardrails.
sicario.review
Review the active spec, plan, tasks, staged changes, or branch for security and governance gaps.
triage-release-check
Triage a failed make release-check — read the captured log, identify the failing gate stage, and recommend the producer-side fix. Analysis only; applies nothing unless asked.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.