What is common-subagent-driven-development?

A workflow for carrying out multi-task coding plans with a fresh helper agent for each task, separate reviews, and a final branch review. It also requires test-driven development, or TDD, where tests are written before the implementation.

It is for executing implementation plans, assigning isolated tasks, applying the red-green-refactor testing cycle, and reviewing the resulting branch.

It reduces context mixing between tasks and adds checks for both whether the requested behavior was implemented and whether the code is sound.

common-subagent-driven-development — Skill by HoangNguyen0403

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.

Any agent

npx skills add HoangNguyen0403/agent-skills-standard --skill common-subagent-driven-development

Clone the repo

git clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standard

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/common-subagent-driven-development/github.svg)](https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/common-subagent-driven-development)

Your own site

<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/common-subagent-driven-development"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/common-subagent-driven-development/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/common-subagent-driven-development"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/common-subagent-driven-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 807 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00045	$0.00807
Opus 5.5	$0.00018	$0.00323
Sonnet 5.5	$0.00009	$0.00161
Haiku 4.5	$0.00005	$0.00081

Measured today against content hash 37e54d6f9548, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-01, from the pricing page.

Security

Grade A, and why

common-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 today.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/review_package.py, scripts/sdd_workspace.py, scripts/task_brief.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/common/common-subagent-driven-development/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagent-Driven Development (SDD)

Priority: P1 (HIGH)

Execute multi-task implementation plans by dispatching a fresh implementer subagent per task, an independent task review (spec compliance + code quality) after each, and a whole-branch review at the end.

1. Execution Confirmation Gate (Scenario A & B)

Before editing code for any multi-task plan:

DO NOT start editing files directly in this orchestrator session.
Confirm with human partner: Offer Subagent-Driven (Recommended — fresh workers via cheap tier + task review gate, zero context bloat) vs. Inline (only for tiny 1-2 file changes).
If approved (or user replies "yes", "proceed", "start"), invoke SDD. See methodology.md.

2. SDD & TDD Integration

Macro (SDD): Orchestrator manages task decomposition, context isolation, review gates, and progress logging.
Micro (TDD): Implementer subagents must follow the strict RED -> GREEN -> REFACTOR cycle inside their assigned brief.

3. Setup & Workspace Resolution

Resolve the isolated, git-ignored workspace directory before Task 1:

python3 skills/common/common-subagent-driven-development/scripts/sdd_workspace.py <PLAN_FILE>

Track task completion in <workspace>/progress.md so work survives context compaction.

4. The Task Loop

For each task in the plan:

Dispatch Implementer: Generate brief via task_brief.py <plan> <N>. Dispatch worker using a cheap execution tier with [BRIEF_FILE] and [REPORT_FILE].
Passive Wait (No Polling): Call wait() and yield control. Never poll status or activity in a loop.
Dispatch Reviewer: Generate package via review_package.py <plan> $BASE $HEAD. Dispatch task reviewer with [BRIEF_FILE], [REPORT_FILE], and [DIFF_FILE].
Fix Loop (Up to 5 Rounds): Re-prompt existing worker via send_agent_prompt with findings; re-review with re-review-prompt.md.

5. Final Review & Completion

Read the full file on GitHub · 74 lines

Files

What ships with it

6 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.

today First seen · 74 lines · 45 tokens per session scan A 37e54d6f9548

Subscribe to this mod's changes

common-subagent-driven-development is a skill published in the GitHub repository HoangNguyen0403/agent-skills-standard (569 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 807 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-01.

Building agents TDD Testing best-practices coding-standards flutter nestjs nextjs

common-subagent-driven-development