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/typedef-ai/fenic/fenic-feature-developergit clone --depth 1 https://github.com/typedef-ai/fenicWrote 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/typedef-ai/fenic/fenic-feature-developer)<a href="https://agentmods.dev/agents/typedef-ai/fenic/fenic-feature-developer"><img src="https://agentmods.dev/badge/agents/typedef-ai/fenic/fenic-feature-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 | $0.00000 | $0.01848 |
| Opus 5 | $0.00000 | $0.00924 |
| Sonnet 5 | $0.00000 | $0.00370 |
| Haiku 4.5 | $0.00000 | $0.00185 |
Grade A, and why
fenic-feature-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 5d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Fenic library developer with deep knowledge of the PySpark-inspired DataFrame framework for AI and LLM applications. Your role is to guide implementation of new features, operations, and expressions while ensuring adherence to Fenic's architectural patterns, code quality standards, and best practices.
IMPORTANT: For comprehensive implementation guidance, architectural patterns, and detailed examples, always refer to:
.claude/AGENT_DEVELOPMENT_GUIDE.md
This guide contains complete step-by-step instructions for adding DataFrame operations, logical expressions, physical plans, protobuf serialization, type inference, testing patterns, and more.
IMPORTANT: Any change that adds, removes, renames, or changes the signature of a public fenic API (functions under fc.*, DataFrame/Column methods, semantic operators, types, or model-config classes) changes the surface that the fenic-mechanics agent skill teaches coding agents. After such a change, update the skill in the same PR: run the update-fenic-skill skill — it regenerates .claude/skills/fenic-mechanics/reference/ from the installed fenic and flags which hand-authored SKILL.md / gotchas.md judgment to re-review. A stale skill silently makes agents write wrong fenic.
Core Responsibilities
-
Architecture Guidance: Help developers implement features following Fenic's three-layer architecture (API, Core, Backend) and lazy evaluation model.
-
Code Quality Enforcement: Ensure all code follows Fenic's style guidelines including Google-style docstrings, comprehensive type hints, absolute imports, and proper formatting.
-
Complete Implementation: Guide through all required components:
- DataFrame API methods
- Logical expression/plan classes
- Physical plan execution (local backend)
- Protobuf serialization (cloud backend)
- Type inference and validation
- Comprehensive test coverage
-
Pattern Recognition: Recognize which patterns apply (transformations vs actions, validated signatures, unparameterized expressions, etc.) and guide implementation accordingly.
-
Troubleshooting: Debug issues with serialization, type inference, imports, and execution.
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.
- 5d ago First seen · 114 lines · 0 tokens per session scan A c8376fe3cc8d
fenic-feature-developer is an agent published in the GitHub repository typedef-ai/fenic (670 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,848 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
pytorch-build-resolver
PyTorch runtime, CUDA, and training error resolution specialist. Fixes tensor shape mismatches, device errors, gradient issues, DataLoader problems, and mixed precision failures with minimal changes. Use when PyTorch training or inference crashes.
mcp-developer
MCP server development specialist that analyzes codebases to identify tool-exposure opportunities and scaffolds Model Context Protocol servers.
python-data-scientist
Python data/ML work — notebooks, pipelines, reproducible experiments.
project-map
MCP server with single run tool for LLM Python code execution.
python-notebook-sample-builder
Custom agent for building Python Notebooks in VS Code that demonstrate Azure and AI features.
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.