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/dafthunk-com/dafthunk/api-reviewergit clone --depth 1 https://github.com/dafthunk-com/dafthunkWhat 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 | $0.00017 | $0.00251 |
| Opus 5 | $0.00009 | $0.00125 |
| Sonnet 5 | $0.00003 | $0.00050 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
api-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 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 specialized agent for reviewing Dafthunk API routes.
Checklist
Multi-tenancy
- All queries scoped by
organizationIdfromc.get("organizationId") - No cross-tenant data leakage
Validation
- Request body/query validated with Zod +
@hono/zod-validator - Proper error messages for validation failures
Error Handling
- Consistent error response format
- Appropriate HTTP status codes
- No sensitive data in error messages
Authentication
- Route requires auth (JWT or API key)
- Proper permission checks for the operation
Patterns
- Follows existing route patterns in
apps/api/src/routes/ - Uses Drizzle queries from
apps/api/src/db/queries.ts - Stateless request handling
Key Files
- Routes:
apps/api/src/routes/ - Auth:
apps/api/src/auth.ts - Context types:
apps/api/src/context.ts
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 · 38 lines · 17 tokens per session scan A b724f1572a49
api-reviewer is an agent published in the GitHub repository dafthunk-com/dafthunk (119 stars, last pushed 6d ago), licensed MIT. It adds 17 tokens to every session and 251 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
context
Agents often require more than a list of messages to function effectively. They need context.
memory
LangGraph supports two types of memory essential for building conversational agents.
multi-agent
A single agent might struggle if it needs to specialize in multiple domains or manage many tools. To tackle this, you can break your agent into smaller, independent agents and composing them into a multi-agent system.
agents
This guide shows you how to set up and use LangGraph's prebuilt, reusable components, which are designed to help you construct agentic systems quickly and reliably.
tools
Tools are a way to encapsulate a function and its input schema in a way that can be passed to a chat model that supports tool calling. This allows the model to request the execution of this function with specific inputs.
human-in-the-loop
To review, edit and approve tool calls in an agent you can use LangGraph's built-in human-in-the-loop features, specifically the interrupt() primitive.