execplan-improve-subagents

Coordinate a two-wave subagent workflow to improve an ExecPlan.

83|4|Updated Mar 17, 2026

Search Tags:#subagents #code-review #software-engineering #ai-workflow #execplan #parallel-review #plan-improvement

Ready to run

npx skills add https://github.com/grp06/slop-janitor --skill execplan-improve-subagents

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: execplan-improve-subagents
Source: https://github.com/grp06/slop-janitor/tree/main/.agents/skills/execplan-improve-subagents
Command: npx skills add https://github.com/grp06/slop-janitor --skill execplan-improve-subagents

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrates a disciplined, code-grounded plan improvement by delegating evaluation to specialized subagents while keeping the parent agent as sole author, reducing risk of drift and missed issues.

Core Features & Use Cases

Two-wave subagent workflow: Wave 1 spawns eight dedicated reviewers on the original plan, Wave 2 spawns two closure reviewers on the rewritten draft.
Parent rewrites the provisional ExecPlan in place while preserving core sections like Progress, Surprises & Discoveries, Decision Log, and Outcomes.
Subagents are read-only and do not directly edit files; the parent produces the final, cohesive plan.
Use when you want code-grounded, parallel-evidence-driven plan improvement and explicit closure checks.
Aligns with Ousterhout design principles to reduce cognitive load and complexity.

Quick Start

Run execplan-improve-subagents to audit and rewrite the current ExecPlan via a two-wave subagent workflow.

Frequently Asked Questions about execplan-improve-subagents

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I improve an ExecPlan using parallel AI subagents?▼

To improve an ExecPlan using parallel AI subagents, run a two-wave workflow where eight dedicated reviewers audit the original plan, then the parent agent rewrites it in place. This delegates evaluation to specialized subagents while keeping the parent as sole author, reducing drift.

Can subagents directly edit my plan files during a code review workflow?▼

No, subagents cannot directly edit plan files during a code review workflow. They operate under a strict read-only policy, meaning the parent agent performs all in-place rewrites to produce the final, cohesive ExecPlan.

What is the best way to audit a software engineering plan with multiple reviewers?▼

The best way to audit a software engineering plan with multiple reviewers is a two-wave subagent workflow. Wave one spawns eight parallel reviewers on the original plan, and wave two spawns two closure reviewers on the rewritten draft to ensure code-grounded improvement.

How do I preserve key sections like Decision Log when rewriting an ExecPlan?▼

To preserve key sections like Decision Log when rewriting an ExecPlan, the parent agent performs in-place rewrites while explicitly maintaining core sections including Progress, Surprises & Discoveries, Decision Log, and Outcomes during the subagent-driven improvement process.

Does the execplan-improve-subagents workflow align with software design principles?▼

Yes, the execplan-improve-subagents workflow aligns with Ousterhout design principles. It structures the plan improvement process to reduce cognitive load and complexity by coordinating specialized subagents for parallel evidence gathering and evaluation.

When should I use a two-wave subagent workflow for plan improvement?▼

You should use a two-wave subagent workflow for plan improvement when you need code-grounded, parallel-evidence-driven evaluation and explicit closure checks. It applies when auditing a plan with parallel reviewers or delegating improvement tasks to subagents.