ds-backend

ds-backend is a skill for Claude Code, Codex from sungurerdim/dev-skills. It costs 45 tokens per session (4,502 once invoked), scanned A, original, MIT.

A design and review guide for the server-side parts of an application, including APIs, databases, login controls, and data pipelines.

In plain words
What is it for?
Use it to design or review REST or GraphQL APIs, database schemas and migrations, authentication and role permissions, or data-import pipelines.
Why use it?
It helps avoid inconsistent API names, database changes that fail later, weak authentication plans, and duplicated data processing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/sungurerdim/dev-skills/ds-backend
Any agent
npx skills add sungurerdim/dev-skills --skill ds-backend
Clone the repo
git clone --depth 1 https://github.com/sungurerdim/dev-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ds-backend

README.md
[![agentmods](https://agentmods.dev/badge/skills/sungurerdim/dev-skills/ds-backend.svg)](https://agentmods.dev/skills/sungurerdim/dev-skills/ds-backend)
Your own site
<a href="https://agentmods.dev/skills/sungurerdim/dev-skills/ds-backend"><img src="https://agentmods.dev/badge/skills/sungurerdim/dev-skills/ds-backend.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,502 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 5.1 $0.00045 $0.04502
Opus 5 $0.00023 $0.02251
Sonnet 5 $0.00009 $0.00900
Haiku 4.5 $0.00005 $0.00450

Measured 3d ago against content hash cfb097098a16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ds-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 3d 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.

ds-backend/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ds-backend

AI-generated APIs ship with inconsistent naming, missing pagination, no auth strategy, schemas that don't survive first migration, and data pipelines that double-process on retry. Skill designs all four layers correctly from start.

Backend Design — API design, database schema, authentication, and data-pipeline architecture in a single skill.

Completion Evidence — applies to every phase: Report done/OK only with the machine-checkable evidence the gates name — the exact command run and its observed output (or file:line diff). Missing evidence → report INCOMPLETE plus what is missing. Self-assessment is never evidence. (This band repeats at file end by design — both copies are normative.)

Triggers

User runs /ds-backend, or asks to design/review an API, database schema, auth flow, or data pipeline.

Triggers — INVOKE / DON'T INVOKE

INVOKE DON'T INVOKE
"design REST API", "design database schema" "implement the endpoint code" (→ manual / ds-fix)
"review OpenAPI spec", "audit DB migration" "audit OWASP / regulatory security" (→ ds-compliance --security)
"design auth flow with OAuth/RBAC" "deploy auth service to production" (→ ds-deploy)
"audit the data pipeline (ingest/ETL/cleaning/retention)" "optimize one pipeline metric via experiments" (→ ds-tune)
"audit API/DB/auth/data-pipeline design conformance" "generic code quality review (readability, duplication)" (→ ds-review)

Contract

Dimensions: B5 (API ergonomics), D3, D4, D5, A10 (OpenAPI spec), A9 (conditional ecosystem rules), C1 (secure-by-design, conditional messaging), D10 (admin API + stats), A11 (webhook/export/embed) Framework alignment (advisory): Google SRE PRR (D3, D4), OpenAPI Specification 3.1+ (A10), OWASP ASVS 5.0 (C1).

  • Covers five scopes: API design, database design, authentication, data pipelines (ingest → clean → merge → store → serve), and LLM/AI features (conditional — only when the project integrates an LLM/AI provider).
  • Generates specifications, not implementation — produces OpenAPI specs, migration files, auth flow diagrams.
  • Only well-established patterns — no experimental or untested approaches.
  • Minimal liability + maximum privacy + minimum deps: auth prioritizes managed services over DIY; data minimization in every schema (responses expose only required fields); prefer platform-native auth over third-party SDKs.
  • Standalone. Uses blueprint profile or ds/audit/findings.md when available; own analysis when absent.
  • State-exempt: audit is regenerable from source; applied fixes land in the working tree — git is the record.
  • Full accounting enforced: every finding and planned check ends in an explicit disposition (fixed / skipped + reason / only you can do); summary totals balance.
  • Pre-existing / out-of-scope errors detected during work are NOT skipped — fixed inline or escalated with concrete blocker.

Read the full file on GitHub · 198 lines

Files

What ships with it

6 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. 3d ago Changed · -151 lines cfb097098a16
  2. 6d ago First seen · 349 lines · 45 tokens per session scan A 277d0ff1e5a8

Subscribe to this mod's changes

ds-backend is a skill published in the GitHub repository sungurerdim/dev-skills (1 stars, last pushed 3d ago), licensed MIT. It adds 45 tokens to every session and 4,502 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

ring:using-lib-systemplane

Using lib-systemplane, the hot-reload runtime-config plane (Postgres LISTEN/NOTIFY or MongoDB change streams), in two modes. Sweep Mode detects DIY config reload (SIGHUP, fsnotify, viper, pgx LISTEN), manual tenant-scoping, hand-built admin CRUD, and v4 residue. Reference Mode catalogs client lifecycle and…

LerianStudio/ring · 106 tokens

ring:using-outbox

Using the transactional-outbox pattern across lib-streaming (writer) and lib-commons/v5/commons/outbox (repository + relay), in two modes. Sweep Mode detects DIY outbox tables, hand-rolled relay loops, send-and-pray emits, missing WithOutboxTx wrapping, and broker calls inside DB transactions. Reference Mode catalogs…

LerianStudio/ring · 98 tokens

ring:mapping-service-resources

Mapping a Go service's Service -> Module -> Resource hierarchy for dispatch-layer registration: detects modules and per-module PostgreSQL/MongoDB/RabbitMQ resources, database names, and shared databases, generates MongoDB index migration pairs (.up.json/.down.json), detects existing Postgres migrations, emits an HTML…

LerianStudio/ring · 97 tokens

performance-audit

Full-stack performance health check across 12 dimensions. Rendering, bundles, assets, API/network, algorithms, memory, database, caching, Web Vitals, backend runtime, concurrency, and framework-specific pathologies. Evidence-based Impact Models with confidence tiers and a prioritized optimization roadmap. Switches…

greglas75/zuvo · 90 tokens

cqrs-event-sourcing-designer

Designs Command Query Responsibility Segregation (CQRS) and Event Sourcing models with projection rebuilders.

codebygarv/Ai-skills · 30 tokens

supabase-node

Express/Hono with Supabase and Drizzle ORM.

alinaqi/maggy · 14 tokens