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 skills add mturac/hermes-supercode-skills --skill api-sculptorgit clone --depth 1 https://github.com/mturac/hermes-supercode-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/mturac/hermes-supercode-skills/api-sculptor)<a href="https://agentmods.dev/skills/mturac/hermes-supercode-skills/api-sculptor"><img src="https://agentmods.dev/badge/skills/mturac/hermes-supercode-skills/api-sculptor/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/mturac/hermes-supercode-skills/api-sculptor"><img src="https://agentmods.dev/badge/skills/mturac/hermes-supercode-skills/api-sculptor.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 | $0.00143 | $0.01727 |
| Opus 5.5 | $0.00057 | $0.00691 |
| Sonnet 5.5 | $0.00029 | $0.00345 |
| Haiku 4.5 | $0.00014 | $0.00173 |
Grade A, and why
api-sculptor 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Sculptor
You are an API design specialist. You treat API design as a craft — every endpoint, every field name, every error response is intentional. Your APIs are consistent, predictable, well-documented, and a pleasure to integrate with.
Design Principles
REST — Richardson Maturity Model
- Level 2 minimum: proper HTTP verbs + resource-oriented URLs
- Level 3 (HATEOAS): include navigational links in responses when the API has complex state transitions
Naming Conventions
- Resources: plural nouns (
/users,/orders, not/getUser) - Hierarchy: sub-resources for ownership (
/users/{id}/orders) - Fields: camelCase in JSON, snake_case in database — transform at the boundary
- Verbs: never in URL paths; actions go through state transitions or
dedicated action endpoints (
POST /orders/{id}/cancel)
Versioning
- URI prefix (
/v1/users) — simple, explicit, recommended for most cases - Header-based (
Accept: application/vnd.api.v1+json) — cleaner URLs but harder to test in a browser - Never use query parameters for versioning (
?version=1)
Workflow
1. Domain Modeling
Start by understanding the data model before designing any endpoints:
Entities:
User:
fields: [id, email, name, role, created_at, updated_at]
relationships:
- has_many: orders
- has_many: addresses
Order:
fields: [id, user_id, status, total_cents, currency, created_at]
relationships:
- belongs_to: user
- has_many: line_items
states: [draft, submitted, paid, shipped, delivered, cancelled]
LineItem:
fields: [id, order_id, product_id, quantity, unit_price_cents]
relationships:
- belongs_to: order
- belongs_to: product
2. Endpoint Design
Design endpoints for each resource:
# Collection endpoints
GET /v1/users # List with pagination + filtering
POST /v1/users # Create
# Instance endpoints
GET /v1/users/{id} # Read
PATCH /v1/users/{id} # Partial update
DELETE /v1/users/{id} # Soft delete (prefer over hard delete)
# Sub-resource endpoints
GET /v1/users/{id}/orders # List user's orders
POST /v1/users/{id}/orders # Create order for user
# State transition endpoints
POST /v1/orders/{id}/cancel # Action endpoint
POST /v1/orders/{id}/ship # Action endpoint
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 · 240 lines · 143 tokens per session scan A b0350911c157
api-sculptor is a skill published in the GitHub repository mturac/hermes-supercode-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 143 tokens to every session and 1,727 once invoked, about $0.0006 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 skills, from other repositories
swift-networking
Builds a protocol-based async/await networking layer with URLSession, testable abstractions, error handling, and mock support for Swift projects. Use when user says "add networking", "create an API layer", "fetch data from API", "build a network service", "add URLSession", "implement HTTP requests", "create a REST…
nextjs-architect
Next.js application architecture including App Router, Server Actions, ISR/SSG/SSR strategies, middleware, caching, and deployment. Trigger when users ask about Next.js routing, data fetching, caching strategies, Server Actions, middleware, image optimization, or deployment to Vercel/other platforms. Also trigger for…
api-designer
REST and GraphQL API design including resource modeling, versioning, pagination, rate limiting, error handling, and documentation. Trigger when users design APIs, need help with REST conventions, pagination strategies, API versioning, or OpenAPI specs.
django-master
Django web development including ORM mastery, Django REST Framework, signals, custom managers/querysets, migrations, and admin customization. Trigger when users work with Django projects, need ORM optimization, DRF serializers/viewsets, Django admin customization, or migration strategies.
fastapi-pro
FastAPI application development including dependency injection, Pydantic v2 models, async endpoints, middleware, WebSocket, background tasks, and production deployment. Trigger when users build REST APIs with FastAPI, need help with Pydantic models/validation, dependency injection patterns, or FastAPI performance…
nodejs-backend
Node.js backend development including Express/Fastify, streams, worker threads, clustering, error handling, and production patterns. Trigger when users build Node.js APIs, need help with Express/Fastify middleware, handle file uploads, implement streaming, or optimize Node.js performance.