Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/butterbase-ai/butterbase-skillsnpx agentmods add skills/butterbase-ai/butterbase-skills/build-appWrote 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/build-app)<a href="https://agentmods.dev/skills/butterbase-ai/butterbase-skills/build-app"><img src="https://agentmods.dev/badge/skills/butterbase-ai/butterbase-skills/build-app/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/skills/butterbase-ai/butterbase-skills/build-app"><img src="https://agentmods.dev/badge/skills/butterbase-ai/butterbase-skills/build-app.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 13 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 56 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Anti-Refusal · line 155 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- high Privilege Escalation · line 322 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 599 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 338 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Data Exfiltration · line 32 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 268 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 279 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 285 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 313 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 482 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 597 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 535 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00038 | $0.05272 |
| Opus 5 | $0.00019 | $0.02636 |
| Sonnet 5 | $0.00008 | $0.01054 |
| Haiku 4.5 | $0.00004 | $0.00527 |
Grade A, and why
build-app scanned grade A 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X PUT "https://s3.amazonaws.com/..." \ How it starts
The opening of the file, as written. The whole thing — 641 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prefer
/butterbase-skills:journey— for a fully guided multi-stage build with preflight, planning, deployment verification, and (optionally) hackathon submission. This one-shot skill remains for users who want the legacy linear setup.
Build a Complete Butterbase App
This skill walks through all seven phases of building a production-ready Butterbase application — from provisioning a backend to deploying a live frontend. Follow each phase in order; later phases depend on artifacts (app_id, schema, RLS policies) produced by earlier ones.
Convention: every JSON body below is the argument object for the tool named in its Tool: header. When the header reads
manage_schemawithaction: "apply", include"action": "apply"alongside the other fields when you make the call.
Phase 1: Create the App
Use init_app to provision an isolated backend with its own database and auto-generated REST API.
Tool: init_app
{
"name": "my-blog"
}
Returns:
{
"app_id": "app_abc123",
"api_base": "https://api.butterbase.ai/v1/app_abc123"
}
Important: Save app_id and api_base — every subsequent tool call requires app_id.
Optional: Generate a Service API Key
If the user needs programmatic access (CI/CD pipelines, server-to-server calls, admin scripts), generate a service key now.
Tool: manage_auth_config with action: "generate_service_key"
{
"name": "Production Deploy Key"
}
⚠️ The full key (
bb_sk_...) is shown only once. Store it securely — it cannot be retrieved again.
Phase 2: Design & Apply Schema
Work with the user to understand their data model before writing any SQL. Ask:
- What are the primary entities (users, posts, products, orders)?
- Which tables are user-owned vs. shared/public?
- What relationships exist between tables (foreign keys)?
- Are there any boolean flags for public visibility (e.g.
published,is_public)?
Preview First with dry_run_schema
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.
- 11d ago First seen · 641 lines · 38 tokens per session scan A 7c33eddc521c
build-app is a skill published in the GitHub repository butterbase-ai/butterbase-skills (533 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 5,272 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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
Provision Postgres + REST API + auth + content-addressed storage + serverless functions + email — paid with x402 USDC on Base. Prototype tier is free on testnet.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
convex-explain-app
Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.
platform-custom-field-generate
Use this skill when users need to create, generate, or validate Salesforce Custom Field metadata. Trigger when users mention custom fields, field types, Roll-up Summary fields, Master-Detail relationships, Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from…