agentleFS
sungminpark-bizsungminpark-biz/tandem-skills/CLAUDE.md

tandem-skills

CLAUDE.md0 starsChanged 7 days agoMITView on GitHub

- Every skill and agent file under skills/ and agents/ has an Antigravity CLI (agy) port under agy/, and README.md has README.ko.md. A change to one goes to its pair in the same commit, or the commit message says no-port: <why>. agy/agents/team-planner.md has no Claude pair (it is the agy agent that Claude's /team starts for the product plan), and agy/skills/team/run-agent.sh + agy/agents/team-survey.md have no Claude pair (they route agy's /team reviews and surveys to exact Gemini 4 Carbon/Hydrogen models…

  • In this repository2 other files it gives its agents.

The file

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

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Every skill and agent file under skills/ and agents/ has an Antigravity CLI (agy) port under agy/, and README.md has README.ko.md.

    line 3
  2. Distinctive:

    After a context compaction Claude Code re-attaches only about the first 5,000 tokens of a skill (the team skill measured ≈2.5 bytes per …

    line 11

≈ “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

Editing this repo

  • Every skill and agent file under skills/ and agents/ has an Antigravity CLI (agy) port under agy/, and README.md has README.ko.md. A change to one goes to its pair in the same commit, or the commit message says no-port: <why>. agy/agents/team-planner.md has no Claude pair (it is the agy agent that Claude's /team starts for the product plan), and agy/skills/team/run-agent.sh + agy/agents/team-survey.md have no Claude pair (they route agy's /team reviews and surveys to exact Gemini 4 Carbon/Hydrogen models on Vertex AI).
  • agy's agents (team-reviewer, team-planner, team-survey) have no tool that writes files or runs commands (file reads, web search): a change that needs git or grep output gives it to them as files.
  • After a context compaction Claude Code re-attaches only about the first 5,000 tokens of a skill (the team skill measured ≈2.5 bytes per token). Keep the re-read paragraph and the safety rules (approval, test data, messages and payments, review) in the first 11 KB of skills/team/SKILL.md (head -c 11000), and the re-read line in agy/skills/team/SKILL.md's description; what falls past 11 KB comes back only through the re-read.
  • A change that makes skills/team/ or agy/skills/team/ bigger says in the PR/commit body how many bytes it adds and what it removed.
  • The repo is public: no service names, customer data, GCP project IDs or one project's rules in the skills.

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.