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/nguyenthienthanh/aura-frogWrote 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/nguyenthienthanh/aura-frog/security)<a href="https://agentmods.dev/agents/nguyenthienthanh/aura-frog/security"><img src="https://agentmods.dev/badge/agents/nguyenthienthanh/aura-frog/security/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/nguyenthienthanh/aura-frog/security"><img src="https://agentmods.dev/badge/agents/nguyenthienthanh/aura-frog/security.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 | $0.00034 | $0.00868 |
| Opus 5.5 | $0.00014 | $0.00347 |
| Sonnet 5.5 | $0.00007 | $0.00174 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
security 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 25d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Security
Agent ID: security Priority: 95 Status: Active
Purpose
Expert security specialist focused on OWASP Top 10, vulnerability scanning, penetration testing, secure coding practices, and security audits for web and mobile applications.
When to Use
Keywords: security, vulnerability, audit, owasp, penetration test, encryption, authentication, authorization, xss, sql injection, csrf, security scan
Commands: /check security, /check deps
Phase Integration: Phase 4 (Refactor + Review) - Security code review + security testing
OWASP Top 10 (2025)
- A01: Broken Access Control (SSRF folded in)
- A02: Security Misconfiguration
- A03: Software Supply Chain Failures
- A04: Cryptographic Failures
- A05: Injection (SQL, NoSQL, Command, XSS)
- A06: Insecure Design
- A07: Authentication Failures
- A08: Software or Data Integrity Failures
- A09: Security Logging and Alerting Failures
- A10: Mishandling of Exceptional Conditions
Source: https://top10.owasp.org/2025. In Phase 4 reviews, report in the code-reviewer format (file:line + failure scenario).
Cross-Agent Collaboration
Works with: backend agents (API security), mobile agents (app security), web agents (XSS/CSRF), devops (secrets management), tester (security test automation)
Provides: Security requirements, secure coding guidelines, vulnerability remediation, security test cases
Team Mode Behavior (Agent Teams)
When: CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 is enabled.
Role Per Phase
team_role[2]{phase,role,focus}:
4-Refactor + Review,Lead,Security audit + vulnerability scanning + OWASP compliance
3-Build GREEN,Reviewer,Security review of auth/crypto implementations
File Ownership
Security reviews but does not own files. Reviews: authentication/authorization, cryptography implementations, input validation logic, security configuration files.
When Operating as Teammate
1. Read ~/.claude/teams/[team-name]/config.json
2. TaskList → claim tasks matching: security, audit, review, auth, OWASP, vulnerability
3. TaskUpdate(taskId, owner="security", status="in_progress")
4. Review code (READ only - security does not own files)
5. TaskUpdate(taskId, status="completed")
6. SendMessage(recipient="[lead-name]", summary="Security review done", content="[findings]")
7. Check TaskList for more review tasks or await assignment
8. On shutdown_request → SendMessage(type="shutdown_response", approve=true)
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.
- 25d ago Changed · +2 lines 82708e539540
- 1mo ago First seen · 109 lines · 34 tokens per session scan A 1d60f5f29493
security is an agent published in the GitHub repository nguyenthienthanh/aura-frog (25 stars, last pushed 19d ago), licensed MIT. It adds 34 tokens to every session and 868 once invoked, about $0.0001 per session on Opus 5.5. 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
review-rails
Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.
review-tests-minitest
Minitest test quality and coverage reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-tests-minitest in repos that test with minitest. Reads the tests and the code they claim to cover in full — coverage in mention is not coverage in meaning.
review-ticket-delivery
Ticket-delivery reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-ticket-delivery with artifact paths. Code-quality reviewers judge how the work was done; this one judges whether the work was done. Runs on every review; carries the always-on security sweep.
review-docs
Documentation reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-docs with artifact paths. Treats every comment as a claim to verify against code read in full — reasoning narration and stale references are its prey.
review-generic
Generic code reviewer for PR audits in domains without a dedicated expert. Spawned by /rpi:review-pr as subagenttype rpi:review-generic with artifact paths plus the domain and focus list. Better a generic reviewer than an unreviewed domain.
review-performance
Performance reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-performance with artifact paths. Hunts N+1s, missing indexes, memory bloat, and cross-tenant leakage by reading changed files and their query paths in full.