agentleFS
ryan-yuuuryan-yuuu/crypto-daytrading-arena/CLAUDE.md

crypto-daytrading-arena

CLAUDE.md129 starsChanged 5 months agoApache-2.0View on GitHub

This file provides guidance to Claude Code, Codex, and other AI coding assistants when working on the crypto trading arena codebase. Project dependencies are managed with uv. - Do not hand-edit pyproject.toml — use uv add <pkg> so uv.lock stays canonical. - Use uv run to execute project files and tests. crypto trading arena uses event-driven agents that consume data streams through Kafka. Each agent is safe to deploy on its own host, and can consume data-streams to make decisions…

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. ryan-yuuu/crypto-trading-arena★ 127100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this CLAUDE.md into the rules it gives an agent

12 rules. About 0 are common, 3 are distinctive, and 9 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 9

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Do not hand-edit pyproject.toml — use uv add <pkg> so uv.lock stays canonical.

    line 8
  2. Very specific:

    Use uv run to execute project files and tests.

    line 9
  3. Distinctive:

    When planned work is large, you may spawn sub-agents to split up or parallelize the work where possible

    line 24
  4. Distinctive:

    Always spawn sub-agents with the opus model and xhigh thinking effort

    line 25
  5. Very specific:

    When implementing any code, please follow test driven development principles using the skill /test-driven-development

    line 30
  6. Very specific:

    Use the skill /pytest-coverage to check your test completeness.

    line 31
  7. Very specific:

    Use /pr-review-toolkit:review-pr to deeply review the code changes for:

    line 35
  8. Distinctive:

    If you run into any verifiable bugs or issues in the calfkit SDK, please create an issue explaining the bug clearly and how to reproduce: …

    line 48
  9. Very specific:

    Use the /grill-with-docs skill when planning and designing features/implementations

    line 52
  10. Very specific:

    Use the /brainstorming skill in addition to /grill-with-docs when the user provides open-ended feature requests without a clear solution or …

    line 53
  11. Very specific:

    Use the /diataxis-docs-writer skill to write documentation.

    line 57
  12. Very specific:

    When an implementation is ready for final review and merge, evaluate whether any decisions during your task qualify for editing or creating …

    line 61

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md files we read have a rule of the same kind, not the same words. “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
CLAUDE.md

crypto trading arena development guide for dummies

This file provides guidance to Claude Code, Codex, and other AI coding assistants when working on the crypto trading arena codebase.

Dependency management and development environment

Project dependencies are managed with uv.

  • Do not hand-edit pyproject.toml — use uv add <pkg> so uv.lock stays canonical.
  • Use uv run to execute project files and tests.

Architecture

crypto trading arena uses event-driven agents that consume data streams through Kafka. Each agent is safe to deploy on its own host, and can consume data-streams to make decisions on realtime data.

Conventions

  • Commits/PRs landing on main use conventional-commit prefixes: feat:, fix:, chore:, docs:, refactor:, test:, perf:, style:. Pick the narrowest accurate one. PR titles follow the same style.
  • Ruff clean for new/changed files.
  • Comments and docstrings explain why, not what.

Sub-agents

  • When planned work is large, you may spawn sub-agents to split up or parallelize the work where possible
  • Always spawn sub-agents with the opus model and xhigh thinking effort
  • Spawn intelligent sub-agents generously for any kind of review work, investigation, and intel gathering. The goal is a wide and deep fan-out.

Test driven development

  • When implementing any code, please follow test driven development principles using the skill /test-driven-development
  • Use the skill /pytest-coverage to check your test completeness.

Deep implementation reviews

  • Use /pr-review-toolkit:review-pr to deeply review the code changes for:
    • functional bugs and issues,
    • anti-patterns,
    • test coverage,
    • documentation correctness & coverage
  • Review implementations using the /simplify skill to surface any potential design or implementation simplifications using more elegant, well-engineered solutions or designs.
  • In certain cases, when prompted, you may have to go through multiple rounds of deep reviews for code changes. In these events, the review is not considered done until the findings from consecutive review rounds converge towards no critical or must-fix issues.
  • Spawn intelligent sub-agents generously for any kind of review work, investigation, and intel gathering. The goal is a wide and deep fan-out.

Development: calfkit agents SDK

  • This project dogfoods the calfkit event-driven and distributed agents SDK.
  • If you reach use cases that calfkit geniunely does not support, causing you to either reach into calfkit internals or implement a hacky workaround, please create a new issue in the calfkit repo, providing a clear explanation of what you were trying to achieve or design and how calfkit's API surface was insufficient: https://github.com/calf-ai/calfkit-sdk/issues
  • If you run into any verifiable bugs or issues in the calfkit SDK, please create an issue explaining the bug clearly and how to reproduce: https://github.com/calf-ai/calfkit-sdk/issues

Design discussions

  • Use the /grill-with-docs skill when planning and designing features/implementations
  • Use the /brainstorming skill in addition to /grill-with-docs when the user provides open-ended feature requests without a clear solution or implementation in mind

Documentation writing

  • Use the /diataxis-docs-writer skill to write documentation.

PR final steps

  • When an implementation is ready for final review and merge, evaluate whether any decisions during your task qualify for editing or creating ADRs. You can refer to the file .agents/skills/grill-with-docs/ADR-FORMAT.md to get guidance on what qualifies.

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.