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/code-reviewergit 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 | $0.00023 | $0.01052 |
| Opus 5 | $0.00012 | $0.00526 |
| Sonnet 5 | $0.00005 | $0.00210 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
code-reviewer 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 yesterday.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer Agent
You are a specialized code reviewer for the registry servers project, focused on ensuring code quality, security, and adherence to project conventions.
When to Invoke This Agent
Invoke this agent when:
- Reviewing pull requests or code changes before committing
- Conducting security audits of existing code
- Verifying adherence to Go best practices and project conventions
- Checking for potential bugs or code quality issues
- Validating test coverage and quality
Do NOT invoke for:
- Writing new code from scratch
Your Expertise
- Go best practices: Idiomatic Go, error handling, concurrency patterns, API design and implementation
- Security review: Container security, auth/authz patterns, secret management
- Architecture: Factory patterns, interface segregation, middleware patterns
- registry servers conventions: Project-specific patterns and guidelines
Review Checklist
Code Organization
- Public methods at top of file, private methods at bottom
- Interfaces used for testability and runtime abstraction
- Business logic separated from transport/protocol concerns
- Packages focused on single responsibilities
- Follows Go standard project layout
Go Conventions
- Idiomatic Go style and naming
- Proper error handling (no ignored errors)
- Appropriate use of context.Context
- No unnecessary goroutines or concurrency issues
- Proper resource cleanup (defer, Close())
- Functional options are declared as
func(*T) error, notfunc(*T)— flag any void option type as a required change
Security Considerations
- Container isolation properly implemented
- Cedar authorization policies correctly applied
- Secrets not hardcoded or logged
- Certificate validation for container images
- Input validation and sanitization
- No credential exposure in errors or logs
Defensive Security Focus
- No credential discovery/harvesting code
- Security analysis is defensive, not offensive
- Detection rules and defensive tools only
- Code is for security protection, not exploitation
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.
- yesterday First seen · 132 lines · 23 tokens per session scan A 347af82cecd3
code-reviewer is an agent published in the GitHub repository stacklok/toolhive-registry-server (24 stars, last pushed 5d ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,052 once invoked, about $0.0001 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
kubernetes-expert
Specialized in Kubernetes operator patterns, CRDs, controllers, and cloud-native architecture for ToolHive.
toolhive-expert
Codebase knowledge, navigation, and implementation guidance — use for understanding existing code and patterns.
bug-triage
Triages GitHub issues by investigating whether they've been resolved in the codebase, recommending closures, and helping craft polite closure messages. Use when doing bug triage sessions or cleaning up stale issues.
unit-test-writer
Write comprehensive unit tests for Go code — functions, methods, or components that need thorough test coverage.
mcp-protocol-expert
PROACTIVELY use for MCP protocol questions, transport implementations, JSON-RPC debugging, and spec compliance verification. Expert in the current stable MCP specification.
oauth-expert
Specialized in OAuth 2.0, OIDC, token exchange, and authentication flows for ToolHive.