AutoBE is an AI tool that turns natural-language backend requirements into a working server application, including its database, APIs, tests, documentation, and implementation. It is for people who want to build and later extend backend prototypes or production applications with AI coding assistants. The catalogue add-ons support workflows around using AutoBE and maintaining its generated applications.
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/wrtnlabs/autobe/add-featurenpx skills add wrtnlabs/autobe --skill add-featuregit clone --depth 1 https://github.com/wrtnlabs/autobeWrote 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/wrtnlabs/autobe/add-feature)<a href="https://agentmods.dev/skills/wrtnlabs/autobe/add-feature"><img src="https://agentmods.dev/badge/skills/wrtnlabs/autobe/add-feature.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 | $0.00015 | $0.01141 |
| Opus 5 | $0.00008 | $0.00571 |
| Sonnet 5 | $0.00003 | $0.00228 |
| Haiku 4.5 | $0.00002 | $0.00114 |
Grade A, and why
add-feature 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 5d 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 207 lines · 15 tokens per session scan A e8123d3e0aa5
add-feature is a skill published in the GitHub repository wrtnlabs/autobe (1,360 stars, last pushed 2mo ago), licensed AGPL-3.0. It adds 15 tokens to every session and 1,141 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 2026-08-30.
Other skills, from other repositories
auth-setup
Implements custom passwordless authentication without Devise. Use when setting up authentication, login flows, session management, passkeys (WebAuthn), magic links, or password resets. Passkeys are the primary auth method; magic links are the fallback. WHEN NOT: For authorization/permissions (use controller concerns…
event-tracking
Builds event tracking, activity feeds, and webhook systems following 37signals patterns with a generic Event model and Eventable concern. Use when implementing audit trails, activity feeds, event recording, webhooks, or when user mentions events, tracking, webhooks, or activity logs. WHEN NOT: For state changes as…
api-patterns
Builds REST APIs using respondto blocks with Jbuilder templates following the 37signals same-controllers-different-formats philosophy. Use when adding API endpoints, JSON responses, token authentication, pagination, or when user mentions API, JSON, REST, or Jbuilder. WHEN NOT: For HTML-only controllers (use…
mailer-patterns
Creates minimal Action Mailer classes with bundled notification patterns following 37signals conventions. Use when sending emails, creating notification systems, digest emails, or when user mentions mailers, emails, notifications, or transactional messages. WHEN NOT: For background job scheduling (use job-patterns)…
multi-tenant-setup
Implements URL-based multi-tenancy with account scoping, membership patterns, and data isolation following 37signals patterns. Use when setting up multi-tenant architecture, account isolation, membership management, or when user mentions multi-tenancy, accounts, or tenant separation. WHEN NOT: For basic model setup…
caching-patterns
Implements HTTP caching with ETags, fragment caching, Russian doll caching, and Solid Cache configuration. Use when optimizing performance, adding caching layers, or when user mentions ETags, freshwhen, stale?, cache keys, or Russian doll caching. WHEN NOT: For Turbo Stream real-time updates (use turbo-patterns), for…