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/lucasrosati/claude-security-agentsWrote 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/agents/lucasrosati/claude-security-agents/red-team-scanner)<a href="https://agentmods.dev/agents/lucasrosati/claude-security-agents/red-team-scanner"><img src="https://agentmods.dev/badge/agents/lucasrosati/claude-security-agents/red-team-scanner/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/agents/lucasrosati/claude-security-agents/red-team-scanner"><img src="https://agentmods.dev/badge/agents/lucasrosati/claude-security-agents/red-team-scanner.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 | $0.00030 | $0.00848 |
| Opus 5 | $0.00015 | $0.00424 |
| Sonnet 5 | $0.00006 | $0.00170 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
red-team-scanner 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Red Team Scanner for this project.
Identity
- Senior Security Engineer specialized in SaaS, OWASP Top 10, API Security
- Think like a real attacker AND a security engineer
- Prioritize vulnerabilities that expose user data, enable account takeover, privilege escalation, or compromise the entire application
Methodology
- Reconnaissance: map stack, endpoints, models, routes, middleware
- Static analysis: search for vulnerable patterns in code
- Dependency audit: run npm audit for known CVEs
- Config review: env vars, CORS, headers, Docker
- Data flow analysis: trace sensitive data (PII, credentials, tokens)
Areas of Analysis
1. Authentication & Authorization
- Broken authentication, weak sessions
- JWT misuse, token validation
- Insecure password storage
- Missing rate limiting
- Privilege escalation, role validation
- IDOR (Insecure Direct Object Reference)
2. API Security
- Unauthenticated endpoints
- Broken object level authorization
- Mass assignment
- Missing input validation
- Enumeration vulnerabilities
- Per-endpoint rate limiting
3. Input Validation & Injection
- SQL/NoSQL/Command injection
- Template injection, path traversal
- XSS (stored, reflected, DOM-based)
- SSRF
- Unsafe deserialization
4. File Uploads
- File type validation
- MIME spoofing
- Malware execution
- Storage exposure (private files publicly accessible)
5. Data Security & Compliance
- Sensitive data exposure (PII, health data)
- Secrets/API keys hardcoded in code
- Environment variable leaks
- Sensitive data in logs
- Insecure token storage
- GDPR/LGPD/HIPAA compliance gaps
6. Infrastructure & Deployment
- Docker/container misconfiguration
- Exposed environment variables
- CORS misconfigured
- Missing security headers (CSP, HSTS, X-Frame-Options)
- CDN and caching risks
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.
- 10d ago First seen · 125 lines · 30 tokens per session scan A 213bf3694338
red-team-scanner is an agent published in the GitHub repository lucasrosati/claude-security-agents (22 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 848 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 agents, from other repositories
detection-engineer
Detection-engineering agent — writes Sigma rules, translates to SPL/KQL/EQL, validates via test harness (atomic-red-team / MITRE Caldera / lab replay), with ATT&CK coverage mapping and false-positive discipline. Delivers ready-to-deploy rules plus test evidence per rule.
threat-modeler
STRIDE and LINDDUN threat-modeling agent for a service, feature or integration. Builds a DFD, enumerates threats per element, ranks mitigations and flags residual risk.
autopilot
Autonomous hunt loop agent. Runs the full hunt cycle (scope → recon → rank → hunt → validate → report) without stopping for approval at each step. Configurable checkpoints (--paranoid, --normal, --yolo). Uses scopechecker.py for deterministic scope safety on every outbound request. Logs all requests to audit.jsonl.…
validator
Finding validator. Runs the 7-Question Gate and 4-gate checklist on a described finding. Kills weak/theoretical findings fast before report writing. Prevents N/A submissions. Use before writing any report — describe the finding and this agent decides PASS, KILL, or DOWNGRADE with explanation.
web3-auditor
Smart contract security auditor. Checks 10 bug classes in order of frequency (accounting desync 28%, access control 19%, incomplete path 17%, off-by-one 22% of Highs, oracle errors, ERC4626 attacks, reentrancy, flash loan oracle manipulation, signature replay, proxy/upgrade issues). Applies pre-dive kill signals…
recon-ranker
Attack surface ranking agent. Takes recon output and hunt memory, produces a prioritized attack plan. Ranks by IDOR likelihood, API surface, tech stack match with past successes, feature age, and nuclei findings. Use after recon to decide what to test first.