agentmods.dev

lmd-subagent-driven-development

lmd-subagent-driven-development is a skill for Claude Code, Codex from dasTholo/lean-md. It costs 70 tokens per session (316 once invoked), scanned A, original, Apache-2.0.

A workflow for executing a .lmd.md implementation plan one task at a time with separate implementer and reviewer agents. It uses shared coordination memory for task briefs, reports, and handoffs.

In plain words
What is it for?
Use it to carry out an existing implementation plan with independent tasks, per-task reviews, and a final review of the complete branch.
Why use it?
It reduces the risk of treating a multi-task plan as one unchecked coding session. Each task receives review for meeting the specification and for code quality, followed by a whole-branch review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

not rated 5repo 1mo ago A scan 70 tokens original Apache-2.0

Good fit Use it to carry out an existing implementation plan with independent tasks, per-task reviews, and a final review of the complete branch.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dastholo/lean-md/lmd-subagent-driven-development
View source ↗ dasTholo/lean-md
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add dasTholo/lean-md --skill lmd-subagent-driven-development
Clone the repo
git clone --depth 1 https://github.com/dasTholo/lean-md

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for lmd-subagent-driven-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/dastholo/lean-md/lmd-subagent-driven-development/github.svg)](https://agentmods.dev/skills/dastholo/lean-md/lmd-subagent-driven-development)
Your own site
<a href="https://agentmods.dev/skills/dastholo/lean-md/lmd-subagent-driven-development"><img src="https://agentmods.dev/badge/skills/dastholo/lean-md/lmd-subagent-driven-development/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for lmd-subagent-driven-development

Your own site · 80×15
<a href="https://agentmods.dev/skills/dastholo/lean-md/lmd-subagent-driven-development"><img src="https://agentmods.dev/badge/skills/dastholo/lean-md/lmd-subagent-driven-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 316 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.00316
Opus 5.5 $0.00028 $0.00126
Sonnet 5.5 $0.00014 $0.00063
Haiku 4.5 $0.00007 $0.00032

Measured 2mo ago against content hash e3e4c635bd08, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lmd-subagent-driven-development scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

content/skills/lmd-subagent-driven-development/SKILL.md · 27 lines

What it actually says

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
Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 27 lines · 70 tokens per session scan A e3e4c635bd08

Subscribe to this mod's changes

lmd-subagent-driven-development is a skill published in the GitHub repository dasTholo/lean-md (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 316 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsPlanning
Related

lmd-subagent-driven-development compared with skills from other repositories

lmd-subagent-driven-development next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lmd-subagent-driven-developmentdasTholo/lean-mdSkill51mo agoApache-2.0A70Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex