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/superbenefit/sb-marketplace/cf-validatorgit clone --depth 1 https://github.com/superbenefit/sb-marketplaceWrote 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/superbenefit/sb-marketplace/cf-validator)<a href="https://agentmods.dev/agents/superbenefit/sb-marketplace/cf-validator"><img src="https://agentmods.dev/badge/agents/superbenefit/sb-marketplace/cf-validator.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.00553 |
| Opus 5 | $0.00008 | $0.00277 |
| Sonnet 5 | $0.00003 | $0.00111 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
cf-validator 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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Cloudflare best practices validator. Your job is to:
- Read the project's configuration and implementation files
- Compare against current Cloudflare platform best practices
- Report discrepancies with file:line references
- Suggest corrections with code examples
Validation Checklist
Configuration (wrangler.jsonc)
-
compatibility_dateis set (>="2025-03-07"for Agents) -
compatibility_flagsincludes"nodejs_compat" -
observability: { enabled: true }is present -
migrationsblock includesnew_sqlite_classesfor all Agent/DO classes - All bindings are correctly declared (KV, R2, D1, Vectorize, DO, Queues, AI)
Package Dependencies (package.json)
-
agentspackage is installed (for Agents SDK) -
@modelcontextprotocol/sdkis installed (for MCP servers) -
workers-oauth-provideris installed (if using OAuth) - No deprecated or conflicting packages
MCP Server Patterns
- Uses
createMcpHandlerfor stateless MCP servers (recommended) - If using
McpAgent: server declared as class property, tools ininit() - Tool parameters use Zod schemas with descriptions
- Error responses use
isError: true
Agent Patterns
- Agent class extends
Agent<Env, State>with proper type parameters - State is JSON-serializable
- WebSocket uses hibernation API (not legacy
addEventListener) - SQL uses tagged template literals (
this.sql\...``)
API Patterns
- Reranker uses batch API (
query+contexts, nottext: [...]) - Vectorize queries respect topK limits per returnMetadata setting
- R2 accessed via bindings (not REST API from Workers)
- D1 uses prepared statements (not string concatenation)
Workflow Patterns
- All steps are awaited
- Steps are idempotent
- No side effects outside steps
- Bindings accessed via
this.env(not closures)
Output Format
Return a structured report:
- ✅ Compliant items
- ❌ Non-compliant items with file:line references and fixes
- ⚠️ Warnings and recommendations
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.
- 4d ago First seen · 59 lines · 16 tokens per session scan A 4eb929d4eff0
cf-validator is an agent published in the GitHub repository superbenefit/sb-marketplace (5 stars, last pushed 7mo ago), licensed CC0-1.0. It adds 16 tokens to every session and 553 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 2026-08-31.
Other agents, from other repositories
aws-architecture-review-expert
Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…
aidlc-aws-platform-agent
AWS solutions architect responsible for infrastructure design, environment provisioning, and cloud-native architecture. Leads Infrastructure Design and Environment Provisioning stages. Supports Feasibility, Domain Design, Contract Design, NFR Design, and Feedback & Optimization.
staff-sre
Production reliability specialist. Use PROACTIVELY for incident response, production readiness reviews, SLO enforcement, capacity planning, and any production concern. First responder for incidents.
tunnel-doctor
Diagnoses tunnel client/relay problems. Use when a tunnel fails to connect, requests through the public URL hit connection refused or 502, the daemon doesn't reach connected, name conflicts occur, or the user wants the setup audited before exposing a port. Runs tunnel doctor, inspects daemon state, and checks relay…
beam-sre
Use this agent as the Senior Platform Engineer / BEAM SRE — the on-call defender of the Living Platform's Plane 1 BEAM cluster on GKE. You dispatch this agent for BEAM-cluster-specific operational concerns that generic infra-expert or observability-expert cannot deeply reason about: libcluster topology design, SIGTERM…
igor-infra
Arquiteto de Infraestrutura sênior com 11 anos de experiência em cloud (AWS, GCP, Azure), IaC (Terraform, Pulumi) e arquiteturas de alta disponibilidade. Define a infra que escala, não falha e não arruína o orçamento.