fenic AGENTS.md

fenic AGENTS.md is an instructions file for Codex, OpenCode from typedef-ai/fenic. It costs 787 tokens per session, scanned A, original, Apache-2.0.

Project instructions for developing and documenting Fenic, a Python library for processing structured data in DataFrames. They describe Fenic-specific behavior, naming, model configuration, and checks that are easy to get wrong.

In plain words
What is it for?
Use them when writing or editing Fenic pipelines, checking imports and namespaces, configuring language or embedding models, and running the Fenic static check.
Why use it?
They help prevent mistakes caused by assuming Fenic works exactly like similar DataFrame libraries such as PySpark or pandas.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/typedef-ai/fenic/agents-md
Clone the repo
git clone --depth 1 https://github.com/typedef-ai/fenic

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for fenic AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/typedef-ai/fenic/agents-md.svg)](https://agentmods.dev/instructions/typedef-ai/fenic/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/typedef-ai/fenic/agents-md"><img src="https://agentmods.dev/badge/instructions/typedef-ai/fenic/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 787 This file is loaded in full into every session.
When invoked 787 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00787 $0.00787
Opus 5 $0.00394 $0.00394
Sonnet 5 $0.00157 $0.00157
Haiku 4.5 $0.00079 $0.00079

Measured 5d ago against content hash 65765876b735, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fenic AGENTS.md 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.

AGENTS.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — writing fenic

fenic is a PySpark-style semantic DataFrame library (import fenic as fc). You likely know its DataFrame surface; below are the mechanics that DON'T match PySpark/pandas intuition. (Developing fenic itself? See CLAUDE.md.)

After writing or editing any fenic pipeline, run fenic check <file> — a static lint (no execution) that resolves your fc.* symbols against the installed fenic and flags namespace/import mistakes.

Must-knows

  • import fenic as fc; everything is flat on fc. There is no fenic.functions, no fenic.api.types, and no unified OpenAIModelConfig.
  • Function namespaces: fc.text / fc.json / fc.markdown / fc.semantic / fc.embedding / fc.dt, and fc.arr for array ops (⚠️ fc.array is the array-literal constructor, not the ops namespace).
  • explode / unnest are DataFrame methodsdf.explode("c"), df.unnest("c") — never fc.explode.
  • Language vs embedding models are separate classes (fc.OpenAILanguageModel vs fc.OpenAIEmbeddingModel) in separate config keys (language_models / embedding_models); default_language_model / default_embedding_model are required when more than one is registered. Anthropic uses split input_tpm / output_tpm, not a single tpm.
  • Semantic templates use Jinja2 {{ var }} + matching column kwargs: fc.semantic.predicate("... {{ x }} ...", x=fc.col("x")). parse_pdf is fc.semantic.parse_pdf (under semantic, not markdown).
  • Local extras for heavier operators: fc.semantic.parse_pdf and session.read.pdf_metadata need fenic[pdf]; df.semantic.with_cluster_labels needs fenic[cluster]; df.semantic.sim_join needs fenic[sim-join].

Traps fenic check can't catch — get these right by hand

  • fc.json.jq(col, q) returns an array.get_item(0) before a scalar .cast.
  • A semantic template with single braces {x} is not interpolated (silent).
  • fc.dt.datediff(end, start) returns end - start (argument order matters).
  • fc.dt.to_timestamp(col, fmt) takes Spark/Java patterns (yyyy-MM-dd HH:mm:ss), not Python %-tokens.

Read the full file on GitHub · 55 lines

Changes

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.

  1. 5d ago First seen · 55 lines · 787 tokens per session scan A 65765876b735

Subscribe to this mod's changes

fenic AGENTS.md is an instructions file published in the GitHub repository typedef-ai/fenic (670 stars, last pushed 3d ago), licensed Apache-2.0. It adds 787 tokens to every session, about $0.0039 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 2026-08-30.