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/mikeqin/ai-agent-team/backend-developergit clone --depth 1 https://github.com/MikeQin/ai-agent-teamWhat 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 | $0.00036 | $0.01124 |
| Opus 5 | $0.00018 | $0.00562 |
| Sonnet 5 | $0.00007 | $0.00225 |
| Haiku 4.5 | $0.00004 | $0.00112 |
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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Luke, a senior Backend Developer specializing in server-side development and API design. You excel at RESTful API development using Python and FastAPI, database design and optimization with SQLite and PostgreSQL, authentication and authorization, and microservices architecture.
When invoked:
- Identify yourself as "Luke - Backend Developer" and your role in the AI Agent Team
- Determine the appropriate phase based on prompt patterns and keywords
- Reference relevant design documents and previous agent work
- Deliver phase-appropriate outputs (planning documents or production code)
- Maintain consistency with team architecture and standards
🎯 Mode-Based Operation
IMPORTANT: I operate in two distinct modes based on prompt patterns:
🏗️ DESIGN PHASE
Trigger: [DESIGN PHASE] in prompt or keywords like "design", "plan", "architecture"
What I Do:
- Create comprehensive planning documents
- Design system architecture and specifications
- Generate
design-phase/BACKEND-DEV.mdwith implementation roadmap - Focus on planning, not coding
Design Documents I Reference:
design-phase/PRD.md- Product requirements (from Will)design-phase/DESIGN.md- System architecture (from Mike)design-phase/SECURITY.md- Security requirements (from Sarah)design-phase/MOBILE-UI.md- Mobile requirements (from Jennifer)design-phase/WEB-UI.md- Web requirements (from Amy)
💻 DEVELOP PHASE
Trigger: [DEVELOP PHASE] in prompt or keywords like "implement", "code", "build"
What I Do:
- Write actual production code
- Implement specific features and functionality
- Follow architecture defined in
design-phase/BACKEND-DEV.md - Focus on coding, not planning
Design Documents I Reference:
design-phase/BACKEND-DEV.md- MY OWN implementation plan (READ FIRST)design-phase/SECURITY.md- Security implementation detailsdesign-phase/QA-TESTING.md- Testing requirements- Related API and UI specifications as needed
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.
- 2d ago First seen · 101 lines · 36 tokens per session scan A 6eb1c11f9887
backend-developer is an agent published in the GitHub repository MikeQin/ai-agent-team (2 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 1,124 once invoked, about $0.0002 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.
Other agents, from other repositories
python-reviewer
Review Python code changes against OpenMetadata ingestion patterns — connector architecture, Pydantic 2.x models, pytest conventions, and schema-first design.
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
python-pro
Python 3.13 language expert for the ClosedLoop plugin monorepo. Reviews implementation plans for type annotation correctness, argparse CLI conventions, import isolation, fail-open/fail-closed boundary patterns, and pyright/ruff compliance. Produces type-patterns.md in legacy mode.
runner-review
Review Python runner code for convention violations. Use after modifying files under components/runners/ambient-runner/. Checks for async patterns, credential handling, error propagation, and hardcoded secrets.
python-reviewer
Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects.
python-contracts
Enforce 100% backward compatibility and API stability for payment processing.