subagent-driven-development

A development workflow that assigns separate, newly started AI agents to individual tasks, then reviews their work for requirements and code quality. A subagent is a separate helper agent given a focused assignment.

In plain words
What is it for?
Use it to split a larger implementation into independent tasks, run them in parallel where appropriate, and check each result for specification compliance and maintainability.
Why use it?
It limits confusion from carrying too much context between tasks and adds review checkpoints. Clear instructions also make the expected files, tests, boundaries, and verification steps explicit.

Skill for Claude CodeCodex

Part of the shipworthy plugin — 41 skills, 7 commands, 6 agents, 3 hooks shipped together

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/vimalk0703/shipworthy/subagent-driven-development
Any agent
npx skills add Vimalk0703/shipworthy --skill subagent-driven-development
Clone the repo
git clone --depth 1 https://github.com/Vimalk0703/shipworthy

Made for: Claude Code, Codex.

Or install shipworthy, the plugin that ships this one along with the rest of its 41 skills, 7 commands, 6 agents, 3 hooks.

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 468 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.00468
Opus 5 $0.00015 $0.00234
Sonnet 5 $0.00006 $0.00094
Haiku 4.5 $0.00003 $0.00047

Measured 3d ago against content hash 36ff8ac47554, 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 3d 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/collaboration/subagent-driven-development/SKILL.md · 62 lines

What it actually says

Subagent-Driven Development

Why Subagents?

Fresh subagents per task provide:

  • Context isolation — no accumulated confusion from prior tasks
  • Precise instructions — each agent gets exactly what it needs
  • Parallel execution — independent tasks run simultaneously
  • Quality gates — two-stage review catches issues early

Dispatch Pattern

For each task in the plan:

1. Craft the Subagent Prompt

Include:

  • Task description — what to build, with exact file paths
  • Architecture constraints — relevant Mandatory Rules from architecture.md
  • Testing requirements — what tests to write (TDD: test first)
  • Verification command — what to run to prove it works
  • Boundaries — what files NOT to touch, what patterns to follow

2. Launch the Subagent

Use the Agent tool with a clear, complete prompt. The subagent should be able to work autonomously without asking questions.

3. Two-Stage Review

Stage 1: Spec Compliance
  • Does the output match the task requirements?
  • Are all specified files created/modified?
  • Do the tests cover the required behavior?
Stage 2: Code Quality
  • Does it follow architecture.md conventions?
  • Is error handling proper?
  • Are there security concerns?
  • Is the code readable and maintainable?

4. Fix Loop

If either stage fails:

  1. Identify specific issues
  2. Send fixes back to a new subagent (or fix directly)
  3. Re-review until both stages pass

When to Use Subagents vs Direct Execution

  • Subagents: independent tasks, well-defined scope, tasks that benefit from fresh context
  • Direct: quick fixes, tasks that depend on conversation context, exploratory work

Key Rule

Each subagent gets the FULL context it needs. Never assume a subagent knows something from the parent conversation.

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. 3d ago First seen · 62 lines · 31 tokens per session scan A 36ff8ac47554

Subscribe to this mod's changes

subagent-driven-development is a skill published in the GitHub repository Vimalk0703/shipworthy (7 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 468 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

roam

Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…

Cranot/roam-code · 86 tokens

ring:writing-plans

Writing a rolling-wave phased implementation plan from a spec before coding: a phase-epic-task hierarchy where Phase 1 is detailed into dispatch-ready tasks and later phases stay epic-level for elaboration during execution. Use when a multi-file feature needs decomposition; runs after ring:exploring-codebases or…

LerianStudio/ring · 94 tokens

ring:searching-code

Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…

LerianStudio/ring · 74 tokens

ring:exploring-codebases

Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…

LerianStudio/ring · 91 tokens

ring:writing-skills

Writing or editing a Ring skill: SKILL.md structure, frontmatter and Agent-Search-Optimization rules, token-efficiency targets, and bulletproofing (Iron Law, rationalization tables, Red Flags) so discipline-enforcing skills resist excuses. Use when creating or revising a skill. Delegates pressure-testing to…

LerianStudio/ring · 100 tokens

ring:applying-licenses

Applying or switching a repository's license (Apache 2.0, Elastic License v2, or Proprietary): rewrites the LICENSE file, updates Go/TS source headers, sets SPDX identifiers, and validates consistency after user confirmation. Use when asked to set, apply, or switch a license, or when scaffolding a service with no…

LerianStudio/ring · 94 tokens