subagent-driven-development

A development workflow for carrying out implementation plans through separate, independent tasks. TDD, or test-driven development, is not explained or mentioned in the input.

In plain words
What is it for?
It is used when executing an existing plan whose work can be split into separate implementation tasks.
Why use it?
It can organize larger implementation plans into smaller tasks that can be handled independently.

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/ralph-workflow/ralph-workflow/subagent-driven-development
Any agent
npx skills add Ralph-Workflow/Ralph-Workflow --skill subagent-driven-development
Clone the repo
git clone --depth 1 https://github.com/Ralph-Workflow/Ralph-Workflow

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 7,481 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.07481
Opus 5 $0.00009 $0.03741
Sonnet 5 $0.00003 $0.01496
Haiku 4.5 $0.00002 $0.00748

Measured 2d ago against content hash 8dd1b8e698ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

subagent-driven-development scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

delete this plan's workspace (`rm -rf <workspace>`) — the git history is
.opencode/skills/subagent-driven-development/SKILL.md · 569 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Files

What ships with it

1 file 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 · 569 lines · 17 tokens per session scan C 8dd1b8e698ed

Subscribe to this mod's changes

subagent-driven-development is a skill published in the GitHub repository Ralph-Workflow/Ralph-Workflow (5 stars, last pushed 2d ago), licensed AGPL-3.0. It adds 17 tokens to every session and 7,481 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

feature-execution

This skill should be used when the user asks to "orchestrate the feature", "run the phases", "resume implementation", "continue the plan", "the phase agent died", "the agent stopped on its usage limit", "accept this phase", "can these phases run in parallel", "is this phase done", "does this shortfall matter", or…

Langerrr/zforge · 219 tokens

acceptance-agent

Use this agent when a zforge phase has reported DONE and its evidence must be independently verified before the planner accepts it. Typical triggers include $zforge:feature-orchestrate accepting a REPORTED phase during a long chain, and any run where the planner's context is the constrained resource. It reconciles the…

Langerrr/zforge · 134 tokens

phase-agent

Use this agent when a phase of a zforge feature plan is ready to implement and its work should run in its own context. Typical triggers include $zforge:feature-orchestrate spawning a READY phase, resuming a phase whose agent was interrupted mid-run, and re-running a phase after a decision was rejected in review. See…

Langerrr/zforge · 101 tokens

template-conventions

This skill should be used when the user asks to "plan a feature", "what goes in the phase file", "which file owns this", "what evidence class is this", "how do I verify a claim no test can settle", "where should this doc go", or when writing, reading or updating any zforge feature document under docs/{feature}/.…

Langerrr/zforge · 107 tokens

async-reasoning

This skill should be used when implementing or designing code with async data flows — "state management design", "async data flow", "stale data", "cache invalidation", "optimistic update", "init order", "race condition", "write then read", "data not updating", "cache not refreshing", "UI shows old data after save"…

Langerrr/zforge · 121 tokens

retro

This skill should be used when the user asks to "retro", "evaluate zforge", "review plugin performance", "score this session", or wants to assess how well zforge's workflow served a feature. Evaluates zforge's workflow scaffolding, not the project's technical decisions or LLM reasoning quality.

Langerrr/zforge · 64 tokens