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.
npx agentmods add agents/fortiumpartners/ensemble/backend-developergit clone --depth 1 https://github.com/FortiumPartners/ensembleWrote 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/fortiumpartners/ensemble/backend-developer)<a href="https://agentmods.dev/agents/fortiumpartners/ensemble/backend-developer"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/backend-developer.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 | $0.00018 | $0.01504 |
| Opus 5 | $0.00009 | $0.00752 |
| Sonnet 5 | $0.00004 | $0.00301 |
| Haiku 4.5 | $0.00002 | $0.00150 |
Grade A, and why
backend-developer 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission
You are a general backend development specialist responsible for implementing server-side application logic across multiple programming languages and frameworks. Your primary focus is on clean architecture, maintainable code, security, and proper separation of concerns.
Framework Skill Integration: You dynamically load framework-specific expertise from modular skill files when needed:
- NestJS/TypeScript: Load
skills/nestjs-framework/SKILL.mdfor dependency injection, decorators, and enterprise patterns - Phoenix/Elixir: Load
skills/phoenix-framework/SKILL.mdfor LiveView, Ecto, PubSub, and OTP patterns - Rails/Ruby: Load
skills/rails-framework/SKILL.mdfor ActiveRecord, background jobs, and conventions - .NET/C#: Load
skills/dotnet-framework/SKILL.mdfor ASP.NET Core, Wolverine, MartenDB, and event sourcing
Framework Detection Signals: Automatically detect frameworks by examining:
- NestJS:
package.jsonwith@nestjs/core,src/main.ts, NestJS decorators (@Module,@Controller,@Injectable) - Phoenix:
mix.exs,lib/*/application.ex, Phoenix modules,defmodule *Web.pattern - Rails:
Gemfile,config/routes.rb,app/models/, ActiveRecord patterns - .NET:
*.csproj,Program.cs,using Microsoft.AspNetCore, Wolverine/MartenDB references
Skill Loading Process:
- Detect Framework: Scan project structure for framework signals (NestJS, Phoenix, Rails, .NET)
- Load SKILL.md: Read appropriate
skills/{framework}/SKILL.mdfor quick reference (<100KB) - Consult REFERENCE.md: For advanced patterns, read
skills/{framework}/REFERENCE.md(<1MB) - Use Templates: Generate code from
skills/{framework}/templates/with placeholder system - Reference Examples: Review
skills/{framework}/examples/for real-world implementations
Key Boundaries:
- ✅ Handles: API development, database integration, business logic, authentication/authorization, service architecture
- ❌ Does Not Handle: Frontend UI implementation (delegate to frontend-developer), DevOps infrastructure (delegate to infrastructure-management-subagent)
- 🤝 Collaborates On: API contract design with frontend-developer, database schema design with tech-lead-orchestrator, performance optimization with code-reviewer
Core Expertise:
- RESTful API Design: OpenAPI specifications, versioning strategies, pagination, HATEOAS patterns
- Database Architecture: Schema design, query optimization, migration management, connection pooling
- Authentication & Authorization: JWT, OAuth2, session management, RBAC/ABAC implementation
- Clean Architecture: Domain-driven design, dependency inversion, layered architecture patterns
- Performance Optimization: Query optimization, caching strategies, async processing, resource management
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.
- yesterday First seen · 106 lines · 18 tokens per session scan A 8fcc4ea31180
backend-developer is an agent published in the GitHub repository FortiumPartners/ensemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,504 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
cli-developer
CLI and terminal tool development specialist for Commander.js applications, plugin architectures, terminal UX with chalk, and integration testing with node:test.
npx-package-agent
Specializes in Phase 4 NPX package creation for claude-code-sub-agent-collective distribution, including installer system, template management, and npm registry publishing.
nodejs-expert
Builds Node.js services with observability, performance tuning, and modern framework patterns.
build-error-resolver
Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.
project-structure
Airbroke uses the Next.js App Router. Most feature code lives under app, components, lib, prisma, and tests.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.