subagent-driven-development

A development workflow that splits an implementation plan into separate tasks handled independently in the current session.

In plain words
What is it for?
It helps carry out multi-step coding plans with independent implementation tasks.
Why use it?
It keeps larger changes organised and reduces the need to manage every subtask as one long piece of work.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/sodiumjoe/dotfiles/subagent-driven-development
Any agent
npx skills add sodiumjoe/dotfiles --skill subagent-driven-development
Clone the repo
git clone --depth 1 https://github.com/sodiumjoe/dotfiles

Made for: Claude Code, Codex.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,845 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00017 $0.04845
Opus 5 $0.00009 $0.02423
Sonnet 5 $0.00003 $0.00969
Haiku 4.5 $0.00002 $0.00485

Measured 2d ago against content hash e5dcf9920f81, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

skills/subagent-driven-development/SKILL.md · 420 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 2d ago First seen · 420 lines · 17 tokens per session scan A e5dcf9920f81

Subscribe to this mod's changes

subagent-driven-development is a skill published in the GitHub repository sodiumjoe/dotfiles (49 stars, last pushed 5d ago), with no licence file. It adds 17 tokens to every session and 4,845 once invoked, about $0.0001 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

create-agent

Create new agents for the code-forge application. Agents are stored as .md files in the /.forge/agents directory with YAML frontmatter (id, title, description, reasoning, tools, userprompt) and markdown body containing agent instructions. Use when users need to add new agents, modify existing agents, or understand the…

tailcallhq/forgecode · 75 tokens

aish-add-skills

Create new skills from documents, tutorials, or examples. Use when user wants to create a skill from learning materials or existing content.

AI-Shell-Team/aish · 32 tokens

taskgo

Maintains a private Git-backed personal project and task control repository using concise current Markdown, derived Git history, ADRs, and status synchronization. Use when tracking tasks, updating project status (STATUS.md), managing ADRs, synchronizing tracker state, or delegating tasks to external agents across…

ithinkihaveacat/dotfiles · 62 tokens

wear-widget

Workflows, checklists, and scripts for reverse-engineering, analyzing, and extracting Wear OS and Android widgets (Glance, AppWidget, ProtoLayout Tiles). Covers manifest declarations, XML configurations, preview asset extraction, and AVD rendering. Use when analyzing APK widget features, extracting widget…

ithinkihaveacat/dotfiles · 81 tokens

mbo-plan

Plan a new objective end-to-end in this repo's docs/mbo Management-By-Objective system — turn a GitHub issue or a gss draft-PR worktree into consistent design/spec/plan artifacts and track it in docs/mbo/index.md. Use this whenever the user wants to START planning or designing a new feature, skill, CLI, or service…

sfc-gh-eraigosa/dotfiles · 260 tokens

jetpack

Looks up AndroidX and Jetpack library facts that change between releases: current artifact versions (ALPHA, BETA, RC, STABLE, SNAPSHOT, build IDs), Maven coordinates for classes/packages, direct dependencies, and published source code. Use when looking up AndroidX/Jetpack library versions, finding Maven coordinates…

ithinkihaveacat/dotfiles · 98 tokens