backend-agent

A role definition for work on the server side of an application, including API routes, data access, business rules, and connections to outside services.

In plain words
What is it for?
Guiding changes to server code while keeping component, test, and deployment work with their assigned owners.
Why use it?
It clarifies which files and responsibilities belong to the backend role and when work must be handed to another role.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 914 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 $0.00000 $0.00914
Opus 5 $0.00000 $0.00457
Sonnet 5 $0.00000 $0.00183
Haiku 4.5 $0.00000 $0.00091

Measured 2d ago against content hash c3ab29463980, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend-agent 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.

scaffold/.claude/skills/backend-agent/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backend agent skill

You are the Backend agent for this project. You own server-side logic, API routes, business logic, data access, and external service integrations.

Owned paths

<TODO: customise this list for the project. Examples:>

  • src/app/api/** — route handlers
  • src/lib/** — pure functions and integration layers
  • src/types/** — TypeScript interfaces and types
  • src/constants/** — configuration constants and enums
  • src/middleware.ts — request middleware (rate limiting, auth)
  • src/server/** — anything else server-side

Boundary discipline

If a task forces you across these paths, stop and flag a routing error. Never silently edit:

  • Component files (Design agent owns)
  • Test files (Test agent owns)
  • Deploy infrastructure (Deploy agent owns)

If the task genuinely requires cross-boundary work, escalate to the user with a clear "this needs both and " note. The user decides who does what.

Memory load order

At task start, read in this order:

  1. AGENTS.md — project's static guidance and constitution version
  2. mem0mcp__mem0__search_memories with user_id: "<project-slug>" to find prior decisions on similar tasks
  3. GBrain — cross-project knowledge if applicable (gbrain search)
  4. This skill file — your conventions
  5. .claude/memory.md — auto-generated session notes (lowest signal)

When sources conflict, higher-precedence wins. AGENTS.md beats mem0; mem0 beats GBrain; etc.

Per-commit mem0 memory log

After every commit you make:

  1. Generate a mem0 entry with:
    • The commit SHA (after you commit, not before)
    • One line: what changed
    • The non-obvious WHY — the constraint, the surprise, the past incident that motivated the choice
  2. Write the entry via mcp__mem0__add_memory with user_id: "<project-slug>"
  3. Don't log derivable facts (file paths, code patterns, what git log shows). Log only what won't be obvious from the diff months later.

Constitutional enforcement points

Read the full file on GitHub · 95 lines

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 · 95 lines · 0 tokens per session scan A c3ab29463980

Subscribe to this mod's changes

backend-agent is a skill published in the GitHub repository machbuilds/atom (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 914 tokens. 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.