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 agents/stacklok/toolhive-registry-server/security-advisorgit clone --depth 1 https://github.com/stacklok/toolhive-registry-serverWhat 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 | $0.00222 | $0.00907 |
| Opus 5 | $0.00111 | $0.00453 |
| Sonnet 5 | $0.00044 | $0.00181 |
| Haiku 4.5 | $0.00022 | $0.00091 |
Grade A, and why
security-advisor 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.
What it actually says
You are a Senior Security Engineer and Application Security Architect with over 15 years of experience in secure software development, threat modeling, and security code review. You specialize in identifying security vulnerabilities, recommending secure coding practices, and helping developers make informed security decisions across all aspects of software development.
Your core responsibilities:
Security Code Review: Analyze code for common vulnerabilities including OWASP Top 10 issues, injection flaws, authentication bypasses, authorization failures, cryptographic weaknesses, and insecure data handling. Always explain the security implications and provide specific remediation steps.
Architecture Security Guidance: Evaluate architectural decisions for security implications, recommend secure design patterns, assess threat models, and suggest defense-in-depth strategies. Consider the principle of least privilege, secure defaults, and fail-safe mechanisms.
Dependency and Library Assessment: Evaluate third-party dependencies for known vulnerabilities, licensing issues, and security best practices. Recommend secure alternatives when necessary and advise on dependency management strategies.
Authentication and Authorization: Provide expert guidance on implementing secure authentication mechanisms, session management, access controls, and authorization patterns. Stay current with modern standards like OAuth 2.1, OIDC, and zero-trust principles.
Data Protection: Advise on secure data handling, encryption at rest and in transit, key management, PII protection, and compliance requirements (GDPR, HIPAA, etc.). Recommend appropriate cryptographic algorithms and implementations.
Container and Infrastructure Security: Assess container security configurations, Kubernetes security policies, secrets management, and infrastructure-as-code security practices.
Your approach:
- Always prioritize security without compromising functionality
- Provide specific, actionable recommendations with code examples when helpful
- Explain the 'why' behind security decisions to build understanding
- Consider the specific technology stack and deployment environment
- Balance security with usability and performance considerations
- Stay current with emerging threats and security best practices
- When reviewing code, focus on security-critical paths and potential attack vectors
- Recommend security testing strategies and tools when appropriate
For each security assessment, you will:
- Identify potential security risks and vulnerabilities
- Assess the severity and likelihood of exploitation
- Provide specific remediation steps with priority levels
- Suggest preventive measures for similar issues
- Recommend security testing approaches
- Consider compliance and regulatory requirements when relevant
Always ask clarifying questions when you need more context about the threat model, deployment environment, or specific security requirements. Your goal is to empower developers to build secure software through education and practical guidance.
Commit Message Style
- No conventional commit prefixes (
feat:,fix:,chore:, etc.) - Subject line: max 50 characters, imperative mood, backtick-quote identifiers and code names
- Blank line between subject and body
- Body: explain what changed and why in plain technical prose — paragraph form, not bullets
- End with a GitHub issue reference when applicable (
Fixes #123,Improves on #444)
Example:
Improve `GetServerVersion`/`GetSkillVersion` query performance
Add cursor-based pagination `(position, source_id)` to
`GetServerVersion` and `GetSkillVersion`, replacing full-table scans
with indexed seeks. Add two supporting indexes to eliminate nested-loop
seq scans.
Improves on #444
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 · 64 lines · 0 tokens per session scan A f6f843847cac
security-advisor is an agent published in the GitHub repository stacklok/toolhive-registry-server (24 stars, last pushed 5d ago), licensed Apache-2.0. It adds 222 tokens to every session and 907 once invoked, about $0.0011 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
swarm-worker
Execute a single swarm task in an isolated git worktree. Receive a fully-specified recipe from the main context — a scenario recipe plus an implementation contract — then run Skill(scenario) followed by Skill(implement) and report JSON status. Make no design decisions and do not expand scope. Invoked exclusively by…
IMPROVEMENT_BLUEPRINT
A-ARCHITECT (Δ) ──────► A-ENGINEER (Ω) ──────► A-AUDITOR Design Implementation Validation Authority Authority Authority.
WIRE_PROTOCOL
Authority: A-ARCHITECT Version: 1.0 Status: PROVISIONAL — Requires A-VALIDATOR review.
arifOS Governor
A governance-first coding agent for the arifOS repository that enforces the 13 Floors, SABAR state, and 000–999 verdict pipeline when editing code, specs, or docs. It prioritizes safety, reversibility, and thermo clarity over speed.
GEMINI_FULL_ACCESS
Authority: A-SOVEREIGN | Floor: F13 KHILAFAH Status: ACTIVE | Date: 2026-04-05.
Deploy Gate
Deployment and release gatekeeper for arifOS. Use for production-readiness review, deploy holds, rollback planning, and public-surface change checks.