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/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/commands/superbenefit/sb-marketplace/validate)<a href="https://agentmods.dev/commands/superbenefit/sb-marketplace/validate"><img src="https://agentmods.dev/badge/commands/superbenefit/sb-marketplace/validate/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/commands/superbenefit/sb-marketplace/validate"><img src="https://agentmods.dev/badge/commands/superbenefit/sb-marketplace/validate.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 | $0.00014 | $0.00614 |
| Opus 5.5 | $0.00006 | $0.00246 |
| Sonnet 5.5 | $0.00003 | $0.00123 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
validate 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 1mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate Cloudflare Implementation
Run a comprehensive validation of the current project against Cloudflare best practices.
Validation Steps
1. Configuration Check (wrangler.jsonc)
Verify:
compatibility_dateis set and appropriate (>="2025-03-07"for Agents SDK)compatibility_flagsincludes"nodejs_compat"observability: { "enabled": true }is presentmigrationsblock hasnew_sqlite_classesfor every Agent/DO class- All required bindings are declared (KV, R2, D1, Vectorize, DO, AI, Queues)
- No stale or orphaned bindings
2. Dependencies Check (package.json)
Verify:
agentspackage installed (for Agents SDK projects)@modelcontextprotocol/sdkinstalled (for MCP servers)workers-oauth-providerinstalled (if using OAuth)- No known deprecated packages
- TypeScript and wrangler are dev dependencies
3. MCP Server Pattern Check
If the project has MCP servers, verify:
- Uses
createMcpHandlerfor stateless servers (recommended pattern) - If using
McpAgent: server is a class property, tools registered ininit() - Tool parameters use Zod schemas with
.describe()annotations - Error responses include
isError: true - OAuth uses
workers-oauth-providerwith proper KV binding
4. API Pattern Check
Verify:
- Reranker uses batch API:
{ query, contexts: [{text}], top_k } - Vectorize queries respect topK limits per
returnMetadatasetting - WebSocket uses hibernation API (not legacy
addEventListener) - SQL uses tagged template literals (
this.sql\...``) - D1 uses prepared statements
- R2 accessed via bindings (not REST API)
5. Workflow Pattern Check (if applicable)
Verify:
- All
step.do()calls are awaited - Steps are idempotent (safe to retry)
- No side effects outside steps
- Bindings accessed via
this.env(not closures) - Return values are JSON-serializable
Output
Report findings as:
- ✅ Compliant: Follows best practices
- ❌ Non-compliant: Must fix (with file:line reference and suggested fix)
- ⚠️ Warning: Should consider (with recommendation)
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.
- 1mo ago First seen · 77 lines · 14 tokens per session scan A dd0ed1018800
validate is a command published in the GitHub repository superbenefit/sb-marketplace (5 stars, last pushed 8mo ago), licensed CC0-1.0. It adds 14 tokens to every session and 614 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 2026-08-31.
Other commands, from other repositories
cost-optimize
Reduce cloud costs across AWS, Azure, and GCP through rightsizing, reserved and spot capacity, storage tuning, and cost monitoring.
deploy
Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.
env
Manage Vercel environment variables. Commands include list, pull, add, remove, and diff. Use to sync environment variables between Vercel and your local development environment.
firebase-publish
Create or reuse a Firebase project, configure Hosting, and deploy the current static site. Never deletes.
scan
Scan AWS account for cost optimization.
finops-status
Orientation — say where an opportunity or assignment sits in the five-step FinOps lifecycle and what unlocks next. Useful when a record has no active stage: an opportunity while its assignments do the work, an assignment whose plan has not been approved yet, or a rejected or archived assignment. Read-only; mutates…