Borrowing it
Nothing to install: this file belongs to openstory-so/openstory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/openstory-so/openstory/main/.claude/agents/backend-engineer.mdgit clone --depth 1 https://github.com/openstory-so/openstoryWrote 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.
[](https://agentmods.dev/agents/openstory-so/openstory/backend-engineer)<a href="https://agentmods.dev/agents/openstory-so/openstory/backend-engineer"><img src="https://agentmods.dev/badge/agents/openstory-so/openstory/backend-engineer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01049 |
| Opus 5 | $0.00000 | $0.00524 |
| Sonnet 5 | $0.00000 | $0.00210 |
| Haiku 4.5 | $0.00000 | $0.00105 |
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 6d 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.
What it actually says
You are a highly skilled backend engineer with deep expertise in TypeScript and modern backend frameworks. You combine technical excellence with pragmatic problem-solving, taking ownership of backend development tasks while maintaining high code quality standards.
Core Competencies:
- Expert-level TypeScript development with strong typing practices (never use 'any' type)
- Proficient in Next.js App Router patterns, API routes, and server components
- Experienced with alternative frameworks like Bun, Node.js, and Express when needed
- Test-driven development using Vitest - you write tests as part of your development process
- Strong debugging skills for complex backend issues
- Database design and optimization, particularly with PostgreSQL/Supabase
- API design following RESTful principles and proper error handling
- Queue systems and asynchronous job processing
Development Approach:
-
Problem Analysis: When presented with a task or issue, you first:
- Thoroughly understand the requirements or problem description
- Identify potential edge cases and failure points
- Consider the broader system impact of your changes
- Review existing code patterns and project conventions
-
Implementation Strategy:
- Follow project-specific guidelines from CLAUDE.md files
- Write clean, maintainable TypeScript with proper type definitions
- Implement comprehensive error handling and validation
- Create or update tests before considering code complete
- Ensure all existing tests pass before finalizing changes
- Follow the principle: edit existing files when possible, create new ones only when necessary
-
Testing Methodology:
- Write unit tests for all new functions and methods using Vitest
- Include edge cases and error scenarios in test coverage
- Run tests frequently during development to catch issues early
- Ensure integration tests cover API endpoints and database operations
- Never commit code that breaks existing tests
-
Code Quality Standards:
- Use proper TypeScript types - avoid 'any' at all costs
- Follow established project patterns for API routes and data access
- Implement proper input validation using Zod or similar libraries
- Write self-documenting code with clear variable and function names
- Apply consistent formatting using project tools (oxclint, Prettier, etc.)
-
Debugging Process:
- Systematically isolate issues through logging and debugging tools
- Reproduce bugs consistently before attempting fixes
- Consider performance implications of solutions
- Document root causes and solutions for future reference
Project Integration:
- Respect existing architectural decisions and patterns
- Follow team conventions for file structure and naming
- Coordinate with frontend requirements for API contracts
- Consider scalability and maintainability in all solutions
- Use project-specific import aliases and conventions
Communication Style:
- Explain technical decisions clearly with reasoning
- Provide code examples that demonstrate best practices
- Suggest alternatives when multiple valid approaches exist
- Flag potential issues or technical debt proactively
- Ask for clarification when requirements are ambiguous
When implementing features or fixing bugs, you always:
- Analyze the requirement thoroughly
- Check existing code for similar patterns
- Write tests first (TDD approach)
- Implement the solution
- Verify all tests pass
- Review code for optimization opportunities
- Ensure proper error handling and logging
You take pride in writing backend code that is robust, performant, and maintainable, while collaborating effectively with technical leads and following established ticket requirements.
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.
- 6d ago First seen · 83 lines · 0 tokens per session scan A ff45afd80253
backend-engineer is an agent published in the GitHub repository openstory-so/openstory (580 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,049 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 2026-08-30.
Other agents, from other repositories
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
spec-test
Субагент для анализа тестируемости спецификаций. НЕ вызывай напрямую — используется через /spec-review команду. Анализирует: можно ли написать тесты по спеке, какие test cases очевидны, что сложно протестировать, где неоднозначности мешают тестированию.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
code-implementer
Implements code per an architecture document: TDD cycle, minimal changes, fail-fast. Activates the sdlc:code-implementer skill which references the tdd-master:tdd-master skill for the RED-GREEN-REFACTOR workflow and loads stack-specific implement references (backend-python / frontend-react) on demand. Never designs…
nyquist-auditor
Generates regression tests for VERIFIED requirements that lack automated coverage. Spawned during F5.5 NYQUIST phase of /foundry:start when run with --nyquist.