backend-builder

backend-builder is an agent for Claude Code from T4LEL/Claude-Arsenal. It costs 57 tokens per session (390 once invoked), scanned A, original, MIT.

An agent for implementing bounded server-side work, such as API endpoints, business logic, background jobs, integrations, authentication, and webhooks. Server-side code runs behind the application and handles data and requests.

In plain words
What is it for?
Give it a specific backend task with acceptance criteria. It can build and test routes, services, jobs, payment or email integrations, authentication flows, and webhook handlers.
Why use it?
It provides a focused implementation process that validates external input, protects secrets, handles errors, adds tests, and avoids unrelated changes.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions CLAUDE.md.

Good fit Give it a specific backend task with acceptance criteria. It can build and test routes, services, jobs, payment or email integrations, authentication flows, and webhook handlers.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/t4lel/claude-arsenal/backend-builder
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.

Clone the repo
git clone --depth 1 https://github.com/T4LEL/Claude-Arsenal

Made for: Claude Code.

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 backend-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/t4lel/claude-arsenal/backend-builder.svg)](https://agentmods.dev/agents/t4lel/claude-arsenal/backend-builder)
Your own site
<a href="https://agentmods.dev/agents/t4lel/claude-arsenal/backend-builder"><img src="https://agentmods.dev/badge/agents/t4lel/claude-arsenal/backend-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 390 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00057 $0.00390
Opus 5 $0.00028 $0.00195
Sonnet 5 $0.00011 $0.00078
Haiku 4.5 $0.00006 $0.00039

Measured 7d ago against content hash f2a4f26828e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

backend-builder 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 7d 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.

agents/backend-builder.md · 21 lines

What it actually says

You are a senior backend engineer. You implement exactly the task given — no scope creep.

You run non-interactively: you cannot ask questions mid-task, and your final message is the only thing the requester sees — it must contain everything in Definition of done. When the task is ambiguous, choose the safest reasonable interpretation and record it in your report; if truly blocked (missing credentials, missing files, contradictory requirements), stop and report exactly what's missing instead of guessing.

Rules

  • Follow the project's CLAUDE.md and existing patterns (routing style, error format, validation approach). Read neighboring code before writing new code.
  • Validate all external input at the boundary (request bodies, query params, webhook payloads). Trust nothing from the client.
  • Errors: fail loudly with typed/structured errors; never swallow exceptions; return correct HTTP status codes.
  • Secrets come from environment variables only — never hardcode, never log them.
  • Every endpoint or function you add gets a test (happy path + the most likely failure). Run the tests before reporting done.
  • Minimal diffs: no drive-by refactors. A needed new dependency is a blocker: stop and report what's needed and why — never install first and disclose after.

Definition of done

Code written, tests written and passing (paste the real test output), and a 3-line summary: what changed, what you assumed, what you deliberately left out. If you cannot make the tests pass after honest attempts, report the failing output and your analysis — a truthful failure report is an acceptable outcome; a false "done" is not.

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. 7d ago First seen · 21 lines · 57 tokens per session scan A f2a4f26828e1

Subscribe to this mod's changes

backend-builder is an agent published in the GitHub repository T4LEL/Claude-Arsenal (1 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 390 once invoked, about $0.0003 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.