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/mtnyilmaz/agents/workflow-subagent-drivennpx skills add mtnyilmaz/agents --skill workflow-subagent-drivengit clone --depth 1 https://github.com/mtnyilmaz/agentsWrote 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.
[](https://agentmods.dev/skills/mtnyilmaz/agents/workflow-subagent-driven)<a href="https://agentmods.dev/skills/mtnyilmaz/agents/workflow-subagent-driven"><img src="https://agentmods.dev/badge/skills/mtnyilmaz/agents/workflow-subagent-driven.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00056 | $0.02359 |
| Opus 5 | $0.00028 | $0.01179 |
| Sonnet 5 | $0.00011 | $0.00472 |
| Haiku 4.5 | $0.00006 | $0.00236 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent-Driven Development
Overview
Execute a plan by dispatching a fresh subagent per task and running two-stage review after each: spec compliance first, then code quality. The main session stays lean — it only coordinates, reviews, and decides.
Core principle: Fresh subagent per task + two-stage review = high quality + fast iteration, without polluting the main session context.
Why subagents: A subagent runs in an isolated context that you construct. You give them exactly the task text, the files they need, and the constraints — nothing else. They cannot inherit your session's history. This keeps them focused and keeps your session clean for coordination.
When to Use
- An implementation plan exists (produced by
workflow-writing-plans) - Tasks are mostly independent — fixing task 2 doesn't require in-memory state from task 1
- You are in an environment that supports subagent dispatch (Claude Code, Codex, Cursor
Tasktool, etc.) - You want to stay in the current session (no context switch)
When NOT to use:
- Tasks are tightly coupled or share in-memory state → use
workflow-executing-plans - No subagent support available → use
workflow-executing-plans - Simple, single-file change → just do it
- Exploratory work without a plan → brainstorm and plan first
The Workflow
Read plan ONCE ─→ Extract all tasks + context ─→ TodoWrite ─→ Per-task loop ─→ Final review ─→ Finishing
│
▼
┌─────────────────────────────────────┐
│ Dispatch implementer subagent │
│ │ │
│ ▼ │
│ Answer questions if any │
│ │ │
│ ▼ │
│ Implementer: code + tests + commit │
│ │ │
│ ▼ │
│ Dispatch SPEC reviewer subagent │
│ │ │
│ ✗ issues → implementer fixes │
│ ✓ pass │
│ ▼ │
│ Dispatch CODE QUALITY reviewer │
│ │ │
│ ✗ issues → implementer fixes │
│ ✓ pass │
│ ▼ │
│ Mark task complete │
└─────────────────────────────────────┘
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.
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.
- 4d ago First seen · 238 lines · 56 tokens per session scan A 0e4938748061
subagent-driven-development is a skill published in the GitHub repository mtnyilmaz/agents (6 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 2,359 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…