Agent-Skills.md

Agent Skills: orchestrated-execution

Execute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.

UncategorizedID: a5c-ai/babysitter/orchestrated-execution

Repository

a5c-ai/babysitter
a5c-aiLicense: MIT
1,52087

Install this agent skill to your local

pnpm dlx add-skill https://github.com/a5c-ai/babysitter/tree/HEAD/library/methodologies/metaswarm/skills/orchestrated-execution

Skill Files

Browse the full folder contents for orchestrated-execution.

Download Skill

Loading file tree…

library/methodologies/metaswarm/skills/orchestrated-execution/SKILL.md

Skill Metadata

Name
orchestrated-execution
Description
Execute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.
  • Executing tasks requiring rigorous quality enforcement
  • When TDD compliance must be verified independently

Process

  1. IMPLEMENT - Coder executes via TDD against spec with DoD items
  2. VALIDATE - Orchestrator independently runs tsc, eslint, vitest (never trusts subagent)
  3. ADVERSARIAL REVIEW - Fresh reviewer checks spec compliance: binary PASS/FAIL with evidence
  4. COMMIT - Only after adversarial PASS, within declared file scope

Anti-Patterns (Enforced)

  • Self-certifying (trusting subagent "tests passed" claims)
  • Combining phases into single steps
  • Reusing reviewers after FAIL
  • Passing previous review findings to new reviewers
  • Treating quality gate failures as advisory

Agents Used

  • agents/coder/ - TDD implementation
  • agents/code-reviewer/ - Fresh adversarial review
  • agents/issue-orchestrator/ - Independent validation

Tool Use

Invoke via babysitter process: methodologies/metaswarm/metaswarm-execution-loop