agentleFS
Sign inStart free
yanzyuyuyanzyuyu/min-tok/skills/enterprise-team/SKILL.md

enterprise-team

Skill1 starsChanged 49 days agoApache-2.0View on GitHub

Lean Multi-Agent & Orchestration Protocol (YAGNI & 200% Token Efficient). Enforces Solo-First execution for single-feature/focused tasks, reserving subagents strictly for decoupled parallel modules.

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:

    When subagents are justified:

    line 35
  2. Distinctive:

    Max 1 Builder + 1 Auditor: Never spawn an army of 4-5 agents.

    line 36

≈ “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

Lean Multi-Agent & Orchestration Protocol (YAGNI Token Shield)

This skill governs when to execute solo versus when to deploy subagents, eliminating token-wasting bureaucracies.

1. The Solo-First Rule (Save 200% Tokens)

Default Operating Mode:

  • For bug fixes, single features, scripts, utilities, tool creation, refactoring, and tasks touching $\le 5$ files: OPERATE IN SOLO MODE.
  • Execute code directly, run inline compilers/linters, and perform self-verification using tyw-audit and automated test scripts.
  • DO NOT spawn subagents for standard tasks. Spawning multi-agent teams for focused work duplicates system prompts and context windows, wasting massive token quotas.

2. When Are Subagents Permitted? (Strict Decoupled Concurrency)

Deploy subagents via invoke_subagent ONLY when:

  1. Decoupled Concurrency: The project requires simultaneous, independent work in distinct domains (e.g., building a full-stack system where Backend API and Frontend UI can be written concurrently in separate directories).
  2. Explicit User Mandate: The user specifically requests a multi-agent team (e.g., using /teamwork-preview).
  3. Heavy Context Isolation: A sub-task requires massive file exploration that would pollute the main conversation's context window.

3. Lean Team Rules (Max 2 Subagents)

When subagents are justified:

  • Max 1 Builder + 1 Auditor: Never spawn an army of 4-5 agents. One builder creates the implementation; one auditor/tester verifies security and functionality.
  • Micro-Diff Auditing: The auditor inspects only git diff or patch outputs, never whole-file dumps.
  • State Preservation: Maintain PROGRESS_STATE.md to track milestones and resume smoothly across server restarts.

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