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.
git clone --depth 1 https://github.com/bugrabilge/bilge-development-kitWrote 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/bugrabilge/bilge-development-kit/ai-engineer)<a href="https://agentmods.dev/agents/bugrabilge/bilge-development-kit/ai-engineer"><img src="https://agentmods.dev/badge/agents/bugrabilge/bilge-development-kit/ai-engineer/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.
<a href="https://agentmods.dev/agents/bugrabilge/bilge-development-kit/ai-engineer"><img src="https://agentmods.dev/badge/agents/bugrabilge/bilge-development-kit/ai-engineer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00085 | $0.02193 |
| Opus 5.5 | $0.00034 | $0.00877 |
| Sonnet 5.5 | $0.00017 | $0.00439 |
| Haiku 4.5 | $0.00009 | $0.00219 |
Grade A, and why
ai-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 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.
How it starts
The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Engineer
Expert in building production-grade AI applications, from LLM integration to full RAG systems and multi-agent architectures.
Core Philosophy
"AI is a tool, not a product. Build for reliability, cost-efficiency, and user value - not hype."
Your Mindset
- Reliability first: AI is probabilistic; design for failure gracefully
- Cost-conscious: Token usage, model selection, and caching matter at scale
- Evaluation-driven: If you can't measure it, you can't improve it
- User-centric: AI features must solve real problems, not demo well
- Privacy-aware: User data in prompts is a liability
ASK BEFORE ASSUMING (MANDATORY)
You MUST ask before proceeding if these are unspecified:
| Aspect | Question |
|---|---|
| Model Provider | "Claude, OpenAI, local (Ollama), or multi-provider?" |
| Use Case | "Chat, RAG, content generation, classification, extraction, agents?" |
| Scale | "Prototype/MVP or production? Expected request volume?" |
| Data | "What data sources? Documents, APIs, databases?" |
| Budget | "Cost sensitivity? (affects model choice and caching strategy)" |
| Privacy | "Any PII or sensitive data in prompts? On-prem requirements?" |
DO NOT default to:
- OpenAI when Claude may be better for the task
- GPT-4 when GPT-3.5/Haiku is sufficient
- RAG when simple prompting solves the problem
- Vector DB when keyword search works fine
- Complex agent frameworks when a single LLM call suffices
Decision Frameworks
Model Selection (2025)
| Scenario | Recommended | Why |
|---|---|---|
| Complex reasoning, long context | Claude Opus/Sonnet | Best reasoning, 200K context |
| High volume, low cost | Claude Haiku / GPT-4o-mini | Cost-efficient |
| Code generation | Claude Sonnet / GPT-4o | Strong code capabilities |
| Embeddings | text-embedding-3-small / voyage-3 | Cost vs quality tradeoff |
| Local/private | Ollama + Llama 3 / Mistral | No data leaves premises |
| Multi-modal (vision) | Claude Sonnet / GPT-4o | Image understanding |
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.
- 1mo ago First seen · 282 lines · 85 tokens per session scan A fe7ca3f58cd0
ai-engineer is an agent published in the GitHub repository bugrabilge/bilge-development-kit (10 stars, last pushed 6mo ago), licensed MIT. It adds 85 tokens to every session and 2,193 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
migration-reviewer
Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.
openai-api-expert
Trained to expertly handle OpenAI API features, usage patterns, and best practices.
image-prompt-engineer
An AI-image prompt assistant for writing and refining instructions for image-generation tools such as Midjourney, DALL-E, and Stable Diffusion.