agentleFS
zedarvateszedarvates/frugal-skills/skills/code-rules/SKILL.md

code-rules

Skill1 starsChanged 30 days agoMITView on GitHub

Guidance for evaluating dependencies, standard-library options, flat architecture, data layout, datastore choices and verification before announcing results. Use before adding a dependency or layer. The full upstream RULES.md and any project-specific file limit are separate prerequisites; do not invent a missing ceiling.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Three taxes: before any dependency: latency, security surface, cold start.

    line 25
  2. Distinctive:

    Verification before announcement: never announce a result without having observed it yourself (service answers on its port, file exists and …

    line 34

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Code Rules — token-efficient coding standards

Package scope and prerequisites

This catalog ships instructions, not the executable runtime. Python modules, scripts, local services and optional tools named below must be installed separately from the upstream project. Check their availability before running commands; if they are missing, explain the prerequisite instead of claiming execution or results. The host agent may use model tokens while following these instructions.

Commands, APIs and runtime behavior described below are conditional examples for a compatible upstream installation; they are not evidence of execution in this package.

"The best optimization is subtraction."

Purpose

These are summarized upstream coding principles to consider while writing. Apply the current project's governing instructions and inspect the full compatible upstream resource before imposing any additional project-specific limit.

Key content:

  • Three taxes before any dependency: latency, security surface, cold start.
  • stdlib first, with the named defaults (http.server, sqlite3 in WAL mode, pathlib, dataclasses with slots, lru_cache).
  • Flat architecture: route -> handler -> datastore, no abstraction circles.
  • Data-oriented design: column-oriented batching for hot paths.
  • Datastore choice by scale (SQLite WAL -> pgvector -> Qdrant -> Milvus).
  • Module registration: each module exposes register(db_path) so the core is never edited to add a feature.
  • File size limit: inspect the actual governing rule before asserting a ceiling; this summary contains no verified numeric limit.
  • Verification before announcement: never announce a result without having observed it yourself (service answers on its port, file exists and was read, process running and responding).

The full RULES.md is a separate upstream workflow resource, not included in this catalog. Obtain the compatible upstream text before relying on omitted tables, commands or limits; if it is unavailable, report that limitation and use only the summary above.

When NOT to use

  • You want structural smells found in existing code — use code_complexity, code_duplication, code_state or code_wrappers.
  • The upstream karpathy-guidelines neighbour is excluded from this catalog pending provenance review; do not assume it is installed.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.