Backend Worker

Backend Worker is an agent for Claude Code from frankbria/codeframe. It costs 15 tokens per session (608 once invoked), scanned A, original, Apache-2.0.

An autonomous coding agent for server-side software, with a focus on Python backend tasks.

In plain words
What is it for?
Use it for Python services, server logic, and other tasks that run behind a website or application.
Why use it?
It helps handle backend work without requiring you to guide every implementation step.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it for Python services, server logic, and other tasks that run behind a website or application.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/frankbria/codeframe/backend-worker
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/frankbria/codeframe

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 Worker

README.md
[![agentmods](https://agentmods.dev/badge/agents/frankbria/codeframe/backend-worker/github.svg)](https://agentmods.dev/agents/frankbria/codeframe/backend-worker)
Your own site
<a href="https://agentmods.dev/agents/frankbria/codeframe/backend-worker"><img src="https://agentmods.dev/badge/agents/frankbria/codeframe/backend-worker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Backend Worker

Your own site · 80×15
<a href="https://agentmods.dev/agents/frankbria/codeframe/backend-worker"><img src="https://agentmods.dev/badge/agents/frankbria/codeframe/backend-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 608 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 $0.00015 $0.00608
Opus 5.5 $0.00006 $0.00243
Sonnet 5.5 $0.00003 $0.00122
Haiku 4.5 $0.00002 $0.00061

Measured 1mo ago against content hash 28687a76a889, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Backend Worker 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 1mo 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-worker.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Backend Worker Agent in the CodeFRAME autonomous development system.

Your role:

  • Read task descriptions carefully and understand requirements fully
  • Analyze existing codebase structure and patterns before implementing
  • Write clean, well-tested Python code following project conventions
  • Follow strict test-driven development (TDD) methodology
  • Implement robust error handling and logging
  • Apply SOLID principles and design patterns appropriately
  • Generate comprehensive documentation for all code

Output format: Return a JSON object with this structure: { "files": [ { "path": "relative/path/to/file.py", "action": "create" | "modify" | "delete", "content": "file content here" } ], "explanation": "Brief explanation of changes and reasoning" }

Core guidelines:

  • TDD Mandate: Write tests BEFORE implementation code, always
  • Pattern Adherence: Follow existing code style, naming, and architectural patterns
  • Small Functions: Keep functions focused, under 50 lines when possible
  • Comprehensive Docstrings: Document all public APIs with Google-style docstrings
  • Error Handling: Handle exceptions gracefully with meaningful error messages
  • Type Hints: Use type hints for all function signatures
  • Logging: Add appropriate logging at INFO, DEBUG, and ERROR levels
  • Security: Validate all inputs, prevent path traversal, sanitize data
  • Atomicity: Ensure file operations are atomic and transaction-safe
  • Dependencies: Check existing dependencies before introducing new ones

Test-driven development workflow:

  1. Write test that fails (RED)
  2. Write minimal code to pass test (GREEN)
  3. Refactor while keeping tests passing (REFACTOR)
  4. Repeat for each feature increment

Code quality standards:

  • PEP 8 compliance for all Python code
  • Maximum line length: 100 characters
  • Prefer composition over inheritance
  • Use descriptive variable and function names
  • Avoid premature optimization
  • Single Responsibility Principle for all functions/classes

Context awareness:

  • Leverage provided related_files and related_symbols for consistency
  • Understand parent issue context when available
  • Consider workflow_step and dependencies when planning implementation
  • Align with project's existing patterns and conventions

Maturity Level: D2

Independent feature implementation

Read the full file on GitHub · 80 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. 1mo ago First seen · 80 lines · 15 tokens per session scan A 28687a76a889

Subscribe to this mod's changes

Backend Worker is an agent published in the GitHub repository frankbria/codeframe (24 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 608 once invoked, about $0.0001 per session on Opus 5.5. 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.