agentmods.dev

jerrycan-backend

A guided workflow for designing and building a backend REST/CRUD API, a web service that lets clients create, read, update, and delete data.

In plain words
What is it for?
Use it to define entities and API behaviour, generate a multi-tenant backend, implement handlers and jobs, and check whether the result is complete.
Why use it?
It turns a written data design into generated models, database migrations, API scaffolding, tests, and documentation while requiring decisions to be confirmed instead of guessed.

Skill for Claude CodeCodex

9 22d ago A scan 92 tokens copy · 100% MIT
View the source file backant-io/jerrycan
Install

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.

agentmods
npx agentmods add skills/backant-io/jerrycan/docs
Any agent
npx skills add backant-io/jerrycan --skill docs
Clone the repo
git clone --depth 1 https://github.com/backant-io/jerrycan

Made for: Claude Code, Codex.

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,530 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00092 $0.05530
Opus 5 $0.00046 $0.02765
Sonnet 5 $0.00018 $0.01106
Haiku 4.5 $0.00009 $0.00553

Measured 2d ago against content hash db0b2d3b0cb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jerrycan-backend 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 2d 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.

Origin

This is a copy

100% identical to jerrycan-backend — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

docs/SKILL.md · 344 lines

How it starts

The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Building a backend with jerrycan

jerrycan turns a single declarative design.json into a working, tested, multi-tenant REST backend: it generates the data layer (SeaORM models, dual-dialect migrations, CRUD repos), typed handler stubs, tenant guards + isolation tests, acceptance tests, OpenAPI, and app wiring. You (the agent) author the design and fill in the handler bodies; jerrycan check is the source of truth for "done."

This skill is a guided process. Work through the phases in order. At each decision point, ask the user — do not guess. Checkpoint after every phase so neither of you loses the thread. The docs are complete and accurate (jerrycan docs --list); read the relevant page before each step rather than guessing an API.

The golden rules

  1. Never guess what to build. If you don't know an entity, a field, a status value, an endpoint, a role, or a behavior — ask. One question at a time.
  2. jerrycan check and the validator are the truth. Loop them; never claim green you haven't seen. Never weaken a generated check to pass it. But a few generated tests are un-greenable BY CONSTRUCTION (a happy-path probe that posts no credential to a login/webhook/API-key endpoint). For those, check will not be fully green and that is correct — recognize them (see Phase 5), leave them, and move on; do NOT thrash trying to green them or weaken the handler.
  3. Read the doc page before using a feature. jerrycan docs <page> / jerrycan explain <CODE>. Start every project by reading jerrycan docs designing.
  4. Flag scope walls EARLY (Phase 2). If the user needs something jerrycan can't express, surface it before you design, and decide together how to handle it.
  5. Checkpoint after each phase: restate what's decided and what's next.

Phase 0 — Orient (once)

  • Confirm jerrycan is available: jerrycan --version (build it if you're in the framework repo: cargo build -p jerrycan then use target/debug/jerrycan).
  • jerrycan docs --list to see the page index. Read jerrycan docs designing now — it is the complete design.json reference (every field, type, constraint, and the gotchas). You will author the design from it.
  • Announce: "I'll use the jerrycan-backend process to design and build this step by step, checking with you at each decision."

Read the full file on GitHub · 344 lines

Files

What ships with it

60 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.

Changes

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.

  1. 2d ago First seen · 344 lines · 92 tokens per session scan A db0b2d3b0cb2

Subscribe to this mod's changes

jerrycan-backend is a skill published in the GitHub repository backant-io/jerrycan (9 stars, last pushed 22d ago), licensed MIT. It adds 92 tokens to every session and 5,530 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to jerrycan-backend, differing in 0 lines, and is treated as a copy.

Backend and APIsFrontendWriting and docs
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens