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 skills/butterbase-ai/butterbase-skills/function-devnpx skills add butterbase-ai/butterbase-skills --skill function-devgit clone --depth 1 https://github.com/butterbase-ai/butterbase-skillsWrote 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/skills/butterbase-ai/butterbase-skills/function-dev)<a href="https://agentmods.dev/skills/butterbase-ai/butterbase-skills/function-dev"><img src="https://agentmods.dev/badge/skills/butterbase-ai/butterbase-skills/function-dev.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 | $0.00037 | $0.02889 |
| Opus 5 | $0.00018 | $0.01444 |
| Sonnet 5 | $0.00007 | $0.00578 |
| Haiku 4.5 | $0.00004 | $0.00289 |
Grade B, and why
function-dev scanned grade B with 1 finding 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
const response = await fetch("https://api.openai.com/v1/chat/completions", { method: "POST", How it starts
The opening of the file, as written. The whole thing — 439 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Serverless Function Development on Butterbase
Guide for developing and deploying serverless functions on Butterbase's Deno runtime. Covers handler signatures, trigger types, database access, environment variables, and testing.
1. Handler Signature
Every function exports a single handler function with this signature:
export async function handler(
request: Request,
context: {
db: PostgresClient, // RLS-aware DB client
env: Record<string, string>, // env vars set on the function
user: { id: string } | null, // present for HTTP+auth:required; null for cron
waitUntil: (p: Promise<unknown>) => void, // background work after Response (≤30s)
idempotency: {
claim: (key: string, opts?: { scope?: string; ttlSeconds?: number }) => Promise<boolean>
} // atomic dedup for webhook retries
}
): Promise<Response>
CRITICAL: The handler MUST return new Response() (Web API standard). Do NOT return plain objects.
Correct:
return new Response(JSON.stringify({ message: "ok" }), {
status: 200,
headers: { "Content-Type": "application/json" }
});
Wrong (will fail):
return { status: 200, body: "ok" }; // NOT a Response object!
2. Trigger Types
HTTP Trigger
Invoke the function via an HTTP request.
{
"trigger": {
"type": "http",
"config": { "method": "POST", "path": "/my-endpoint", "auth": "required" }
}
}
Auth options:
"required"— request must include a valid JWT;ctx.useris always set"optional"— JWT is parsed if present;ctx.usermay benull"none"— public endpoint; no auth needed;ctx.useris alwaysnull
Cron Trigger
Execute the function on a schedule.
{
"trigger": {
"type": "cron",
"config": { "schedule": "0 9 * * *", "timezone": "UTC" }
}
}
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 · 439 lines · 37 tokens per session scan B 7370189b44d1
function-dev is a skill published in the GitHub repository butterbase-ai/butterbase-skills (533 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 2,889 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
butterbase
AI-native, open-source backend-as-a-service with a built-in Model Context Protocol server. Postgres, auth, storage, functions, AI gateway.
run402
Provision Postgres + REST API + auth + content-addressed storage + serverless functions + email — paid with x402 USDC on Base. Prototype tier is free on testnet. Use when the user asks to build a webapp, deploy a site, create a database, generate images, or mentions Run402.
run402-buzz
Complete Run402 onboarding for a managed Buzz agent with a dedicated wallet/public identity link, report independent human-adoption and community-installation state, offer bounded per-agent enrollment before provisioning, and stop only at a real approval or repair boundary. Use when a managed Buzz user says "install…
bugs
Automated bug triage and fix pipeline. Fetches open GitHub Issues, performs root cause analysis, writes failing tests, fixes bugs in isolated worktrees, and publishes. Use when the user says /bugs, "check for bugs", "triage bugs", or "fix reported issues".
run402
Provision Postgres + REST API + auth + content-addressed storage + serverless functions + email — paid with x402 USDC on Base. Prototype tier is free on testnet.
verification
Full catalog of this repo's verification, test, fuzz, bench, and operator commands, plus which test suites are gated behind Minio, credentials, Postgres, or Workerd. Use when a needed command is not in CLAUDE.md's resident table, when a test is skipping and the reason is unclear, or when running benches, mutation…