orchestrated-execution

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

509 stars

Best use case

orchestrated-execution is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

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

Teams using orchestrated-execution should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/orchestrated-execution/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/methodologies/metaswarm/skills/orchestrated-execution/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/orchestrated-execution/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How orchestrated-execution Compares

Feature / Agentorchestrated-executionStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

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

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Orchestrated Execution

## Overview

Execute work units through the Metaswarm 4-phase cycle. Quality gates are blocking state transitions. Adversarial reviews use fresh reviewers with binary PASS/FAIL verdicts.

## When to Use

- Implementing work units from an approved plan
- 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`

Related Skills

implementation-execution

509
from a5c-ai/babysitter

Execute development tasks to build features, producing code, tests, and configuration artifacts that satisfy specification requirements and comply with constitution standards.

spec-execution

509
from a5c-ai/babysitter

6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.

process-builder

509
from a5c-ai/babysitter

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

Workflow & Productivity

babysitter

509
from a5c-ai/babysitter

Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)

yolo

509
from a5c-ai/babysitter

Run Babysitter autonomously with minimal manual interruption.

user-install

509
from a5c-ai/babysitter

Install the user-level Babysitter Codex setup.

team-install

509
from a5c-ai/babysitter

Install the team-pinned Babysitter Codex workspace setup.

retrospect

509
from a5c-ai/babysitter

Summarize or retrospect on a completed Babysitter run.

resume

509
from a5c-ai/babysitter

Resume an existing Babysitter run from Codex.

project-install

509
from a5c-ai/babysitter

Install the Babysitter Codex workspace integration into the current project.

plan

509
from a5c-ai/babysitter

Plan a Babysitter workflow without executing the run.

observe

509
from a5c-ai/babysitter

Observe, inspect, or monitor a Babysitter run.