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.
npx agentmods add skills/vimalk0703/shipworthy/subagent-driven-developmentnpx skills add Vimalk0703/shipworthy --skill subagent-driven-developmentgit clone --depth 1 https://github.com/Vimalk0703/shipworthyWhat 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.
| Model | Per session | Once 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 |
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.
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:
- Identify specific issues
- Send fixes back to a new subagent (or fix directly)
- 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.
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.
- 3d ago First seen · 62 lines · 31 tokens per session scan A 36ff8ac47554
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.
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…
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…
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…
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…
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…
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…