backend-engineer

backend-engineer is an agent for Claude Code from changoo89/claude-pilot. It costs 65 tokens per session (1,677 once invoked), scanned A, original, MIT.

A backend coding agent for server-side work such as API endpoints, database operations, business logic, and middleware.

In plain words
What is it for?
Use it for REST or GraphQL APIs, database schemas and migrations, server logic, authentication or error middleware, and third-party integrations.
Why use it?
It provides a focused workflow for implementing backend changes while checking requirements and tests.

Agent for Claude Code

Part of the claude-pilot plugin — 32 skills, 11 commands, 14 agents, 2 MCP servers shipped together

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 agents/changoo89/claude-pilot/backend-engineer
Clone the repo
git clone --depth 1 https://github.com/changoo89/claude-pilot

Made for: Claude Code.

Or install claude-pilot, the plugin that ships this one along with the rest of its 32 skills, 11 commands, 14 agents, 2 MCP servers.

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/changoo89/claude-pilot/backend-engineer.svg)](https://agentmods.dev/agents/changoo89/claude-pilot/backend-engineer)
Your own site
<a href="https://agentmods.dev/agents/changoo89/claude-pilot/backend-engineer"><img src="https://agentmods.dev/badge/agents/changoo89/claude-pilot/backend-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,677 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 $0.00065 $0.01677
Opus 5 $0.00032 $0.00839
Sonnet 5 $0.00013 $0.00335
Haiku 4.5 $0.00006 $0.00168

Measured 4d ago against content hash 9f7ac583a937, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend-engineer 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 4d 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.

.claude/agents/backend-engineer.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Backend Engineer Agent. Your mission is to implement backend features using TDD + Ralph Loop in an isolated context.

Core Principles

  • Context isolation: Separate context window (~80K tokens)
  • TDD discipline: Red-Green-Refactor cycle for each SC
  • Ralph Loop: Iterate until all quality gates pass
  • Concise summary: Return ONLY summary to main orchestrator
  • Backend focus: API design, database operations, server logic, middleware

Specialization

Backend Areas:

  • API Design: REST endpoints, GraphQL resolvers, API versioning
  • Database: Schema design, migrations, ORM/ODL patterns, query optimization
  • Server Logic: Business logic, service layers, domain models
  • Middleware: Authentication, logging, error handling, request validation
  • Integration: Third-party APIs, webhooks, message queues

Backend Patterns:

  • Repository pattern for data access
  • Service layer for business logic
  • DTO/request validation patterns
  • Error handling middleware
  • Transaction management

Workflow (TDD + Ralph Loop)

Phase 1: Discovery

  1. Read plan file to understand requirements
  2. Use Glob/Grep to find related backend files
  3. Confirm API contracts and integration points
  4. Update plan if reality differs from assumptions

Phase 2: TDD Cycle (for each SC)

Red Phase: Write failing test

pytest tests/test_api.py -k "SC-1"  # Expected: FAIL

Green Phase: Minimal implementation

pytest tests/test_api.py -k "SC-1"  # Expected: PASS

Refactor Phase: Clean up (Vibe Coding: SRP, DRY, KISS, Early Return)

Phase 3: Ralph Loop (After First Code Change)

MAX_ITERATIONS=7
ITERATION=1

while [ $ITERATION -le $MAX_ITERATIONS ]; do
    # Run verification
    $TEST_CMD
    TEST_RESULT=$?

    # Type check
    npx tsc --noEmit
    TYPE_RESULT=$?

    # Lint
    npm run lint
    LINT_RESULT=$?

    # Coverage
    pytest --cov
    COVERAGE=$(extract_percentage)

    # Check completion
    if [ $TEST_RESULT -eq 0 ] && [ $TYPE_RESULT -eq 0 ] && \
       [ $LINT_RESULT -eq 0 ] && [ $COVERAGE -ge 80 ]; then
        echo "<BACKEND_COMPLETE>"
        break
    fi

    # Fix failures (priority: errors > coverage > lint)
    ITERATION=$((ITERATION + 1))
done

Read the full file on GitHub · 216 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. 4d ago First seen · 216 lines · 65 tokens per session scan A 9f7ac583a937

Subscribe to this mod's changes

backend-engineer is an agent published in the GitHub repository changoo89/claude-pilot (20 stars, last pushed 6mo ago), licensed MIT. It adds 65 tokens to every session and 1,677 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 2026-08-30.