agentleFS
Sign inStart free
saimskywalkersaimskywalker/lumenparty/skills/cosmos/SKILL.md

cosmos

Skill0 starsChanged 8 days agoMITView on GitHub

Load when the owner says \"Lumenparty, assemble!\" (show the crew), before handing any work to a subagent, when splitting a feature across parallel agents, and to pick the reviewers a diff needs. Decides self vs agent first.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. ai-ecoverse/skills★ 1same name
    2. shashidharbabu/claude-design-skills★ 0same name
    3. shashidharbabu/rocketride-design-skills★ 0same name

    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 repository13 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    Never for a 1-3 file change, a single lookup, or something already in context.

    line 33
  2. Distinctive:

    Write ONE brief file first (decisions already made, literal contracts: endpoints, JSON keys, routes, i18n keys.

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
SKILL.md

Cosmos: the one who summons

The owner is Cosmos, the one who summons the party. The main session acts in the owner's name and decides who is called.

Summon: "Lumenparty, assemble!"

SHOW the crew, spawn NOTHING. Answer in the owner's language (WOL_LANG in .claude/wol/config.sh), opening with:

「仲間たちよ、クリスタルが汝らを選んだ。集え——このコードに調和を取り戻すために。」 "Party, the crystals have chosen you. Gather, and restore harmony to this code." — Cosmos

Then, one screen: the self-first rule; the heroes (name, role, model, access); the skills and when each loads; the spells; the Crystal Gate; the pipelines, one line each; how to call them ("Cosmos, send Noctis to review PR #12", "Cid, prepare release 2.3.0", "Aerith, run the health check").

0. Self first (mana is precious)

An agent starts with no context and re-reads what the session already knows, so a small job costs MORE through an agent. Work in the main session unless one of these holds:

  • the owner asked for a hero by name;
  • the work splits into independent parts that run in PARALLEL;
  • answering means reading many files and only the conclusion is needed;
  • an independent review is wanted, once per PR-ready point. Never for a 1-3 file change, a single lookup, or something already in context. Say in one line which hero ran and why.

Models: haiku gathers, sonnet builds and reads deep, opus judges risk. Reviewers return a VERDICT block, never diffs or logs.

1. Conditional gates (what the diff touches → whose PASS it needs)

Diff touches (patterns in config.sh)Needs PASS from
WOL_GATE_SECURITY: auth, session, payment, IAP, webhook, admin, uploadnoctis
WOL_GATE_COPY: i18n files, store listing, permission stringsterra
WOL_GATE_DB: migrations, schemashantotto
UI filesrosa (skill, advisory)
WOL_GATE_HUMAN: CI, release, infraa human merges

lumenparty gate <N> --report prints the same list for a PR. (lumenparty is on PATH with the plugin; after install.sh it is .claude/wol/bin/lumenparty.) PASS continues, BLOCK is a fix round, NEEDS-HUMAN stops and asks.

2. A parallel job

Write ONE brief file first (decisions already made, literal contracts: endpoints, JSON keys, routes, i18n keys; an ownership table so no two heroes edit one file; shared files such as the router and i18n stay with the session; the gates). Each prompt: "read brief.md, you are X, touch only your files, return conclusions". Then merge their notes, run each gate once through the Slow queue, review once, commit per area (skill: ignis).

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.

Check your setup, free