Run any Skill in Manus with one click

lmd-subagent-driven-development

Stars4

Forks0

UpdatedJuly 16, 2026 at 15:48

Executes a .lmd.md plan one task at a time — a fresh implementer subagent per task, two-verdict review between tasks, a whole-branch final review — all handoffs over lean-ctx memory/coordination. Use when executing an implementation plan with independent tasks in the current session.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

dasTholo

dasTholo/lean-md

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

5 files

SKILL.md

readonly

name	lmd-subagent-driven-development
description	Executes a .lmd.md plan one task at a time — a fresh implementer subagent per task, two-verdict review between tasks, a whole-branch final review — all handoffs over lean-ctx memory/coordination. Use when executing an implementation plan with independent tasks in the current session.

lmd-subagent-driven-development (delegation stub)

Body renders one phase at a time — never read it from disk. Rendering, diagnosis and fallback: see the lmd-rendering-skills skill.

The skill executes a .lmd.md plan: one fresh implementer subagent per task, a two-verdict review (spec-compliance + code-quality) between tasks, and a whole-branch final review. Every brief, report, diff and baton moves through lean-ctx (ctx_session/ctx_knowledge/ctx_agent) — never through external SDD bash scripts or scratch-ledger files.

Phases

orient → preflight → dispatch-mode → dispatch | parallel-dispatch → review → final-review → handoff.

The dispatch/review/final-review phases compose @dispatch briefs to the three companions.

Companions

implementer — per-task implementation brief (TDD, self-review, escalation)
task-reviewer — two-verdict per-task review (spec-compliance + code-quality)
code-reviewer — whole-branch final review

More from this repository

same repository

lmd-brainstorm

dasTholo/lean-md

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation. Use when starting creative work that will produce a versioned design spec.

2026-07-164

lmd-rendering-skills

dasTholo/lean-md

Use when you need to render an lmd-* skill phase or companion, or when a render call fails and you must decide whether the gateway is broken or the call was misaddressed.

2026-07-164

lmd-test-driven-development

dasTholo/lean-md

Use when implementing any feature or bugfix, before writing implementation code

2026-07-164

lmd-writing-skills

dasTholo/lean-md

Use when creating new skills, editing existing skills, or verifying skills work before deployment

2026-07-164

lmd-dispatching-parallel-agents

dasTholo/lean-md

Fans out one focused subagent per independent problem domain (disjoint files, no shared state), then conflict-scans and integrates. Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.

2026-07-164

lmd-executing-plans

dasTholo/lean-md

Executes a .lmd.md plan in this session — the main agent runs each task itself, pauses at batch checkpoints for human review, and closes at a whole-branch final gate. No companions. Use when executing an implementation plan inline with human review checkpoints.

2026-07-164

name	lmd-subagent-driven-development
description	Executes a .lmd.md plan one task at a time — a fresh implementer subagent per task, two-verdict review between tasks, a whole-branch final review — all handoffs over lean-ctx memory/coordination. Use when executing an implementation plan with independent tasks in the current session.

lmd-subagent-driven-development (delegation stub)

Body renders one phase at a time — never read it from disk. Rendering, diagnosis and fallback: see the lmd-rendering-skills skill.

Phases

orient → preflight → dispatch-mode → dispatch | parallel-dispatch → review → final-review → handoff.

The dispatch/review/final-review phases compose @dispatch briefs to the three companions.

Companions

implementer — per-task implementation brief (TDD, self-review, escalation)
task-reviewer — two-verdict per-task review (spec-compliance + code-quality)
code-reviewer — whole-branch final review