subagent-dev-mode

subagent-dev-mode is a skill for Claude Code from Simone-Tarantino/godot-superpowers. It costs 74 tokens per session (2,053 once invoked), scanned A, original, MIT.

A development workflow in which an organising agent divides a larger implementation into tasks for separate workers, then verifies each file change externally. It is intended for approved milestones or features spanning multiple files or subsystems.

In plain words
What is it for?
Use it to implement a pre-approved multi-file game milestone or feature after the required design and planning work is complete.
Why use it?
It keeps the organising agent’s context smaller while adding an independent check that the workers’ changes are correct.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the godot-superpowers plugin — 33 skills, 15 agents, 4 hooks, 5 MCP servers shipped together

Good fit Use it to implement a pre-approved multi-file game milestone or feature after the required design and planning work is complete.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/simone-tarantino/godot-superpowers/subagent-dev-mode
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 Simone-Tarantino/godot-superpowers --skill subagent-dev-mode
Clone the repo
git clone --depth 1 https://github.com/Simone-Tarantino/godot-superpowers

Made for: Claude Code.

Or install godot-superpowers, the plugin that ships this one along with the rest of its 33 skills, 15 agents, 4 hooks, 5 MCP servers.

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.

agentmods badge for subagent-dev-mode

README.md
[![agentmods](https://agentmods.dev/badge/skills/simone-tarantino/godot-superpowers/subagent-dev-mode.svg)](https://agentmods.dev/skills/simone-tarantino/godot-superpowers/subagent-dev-mode)
Your own site
<a href="https://agentmods.dev/skills/simone-tarantino/godot-superpowers/subagent-dev-mode"><img src="https://agentmods.dev/badge/skills/simone-tarantino/godot-superpowers/subagent-dev-mode.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,053 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.02053
Opus 5 $0.00037 $0.01026
Sonnet 5 $0.00015 $0.00411
Haiku 4.5 $0.00007 $0.00205

Measured 7d ago against content hash c68a35918bc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

subagent-dev-mode 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 7d 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/subagent-dev-mode/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagent dev mode

A workflow that turns Claude into a thin coordinator: real work happens in subagents with isolated context. Main context stays small; correctness is double-checked by an external verifier.

When to use

Use subagent dev mode when all of the following are true:

  1. The matching design trail has cleared. Either:
    • Trail A (greenfield): approved GDD (game-brainstorming + gdd-writer) AND approved plan (writing-game-plan).
    • Trail B (feature on existing game): approved feature spec (feature-spec, optionally informed by codebase-survey) AND approved feature plan (feature-plan).
  2. The current task is implementing a milestone or a feature touching 3+ files or 2+ subsystems.
  3. The user has not asked for a quick one-shot fix.

Do NOT use subagent dev mode for:

  • Single-file edits (call the skill directly — dispatch overhead is not worth it).
  • Brainstorming / planning (those run in main context).
  • Read-only investigations (Explore subagent or direct Grep).
  • Bug fixes with a known root cause (direct edit + code-reviewer).

Activation triggers

Activate this mode when the user says (or implies):

  • "Implement milestone M2"
  • "Build the player + health + hurtbox feature"
  • "Roll out the localization system"
  • "Subagent mode" / "orchestrator mode"
  • "Parallelize this" / "split this work"

Roles

Role Agent Model Reads Writes
Orchestrator orchestrator sonnet plan, GDD, file paths <orchestrator-state> block + plan status
Worker one of the implementation skills/agents sonnet files in its scope the file it owns
Verifier file-verifier haiku one file + project.godot nothing — findings only
Integrator milestone-integrator sonnet plan, verifier verdicts, test outcomes; runs headless smoke plan markdown status flip only
Researcher Explore (built-in) IDE default codebase nothing

Main-context Claude becomes a thin shell: it confirms preconditions, hands the milestone to the orchestrator, relays the orchestrator's report to the user, and asks the next question.

Read the full file on GitHub · 158 lines

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. 7d ago First seen · 158 lines · 74 tokens per session scan A c68a35918bc2

Subscribe to this mod's changes

subagent-dev-mode is a skill published in the GitHub repository Simone-Tarantino/godot-superpowers (2 stars, last pushed 4mo ago), licensed MIT. It adds 74 tokens to every session and 2,053 once invoked, about $0.0004 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

game-build-team

Build a Godot 4 / GDScript game feature with a coordinated agent team — a Manager (you), a Creative Director, a Logic Developer, an Animation Developer, and a Tester — that iteratively and autonomously design, build, juice, and verify the feature against the project's design contract to a strict, un-skippable quality…

Varalix-Digitech-Solutions/game-build-team-skill · 248 tokens

content-planner

GSC-driven content calendar. Pulls real Search Console data, finds the highest click-potential opportunities (striking-distance queries at positions 5-20, unanswered query intent, related-keyword expansions), and produces a dated, prioritized content calendar — ready to hand to /content-writer. Use when the user asks…

nowork-studio/notfair-plugin · 123 tokens

setup-cms

Connect a CMS to notfair SEO tools. Guides users through configuring WordPress, Strapi, Contentful, or Ghost — tests the connection, and writes credentials to .env.local. Once set up, seo-analysis automatically cross- references CMS content against Google Search Console data. Use whenever the user says "connect my…

nowork-studio/notfair-plugin · 111 tokens

broken-link-checker

Scans a website to find broken links (404s, 500s). Crawls internal pages, identifies broken outbound links, and reports source pages for easy fixing. Use this when the user asks to "check for broken links", "find 404s", "audit my links", or "is my site healthy".

nowork-studio/notfair-plugin · 72 tokens

google-ads-audit

Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…

nowork-studio/notfair-plugin · 114 tokens

google-ads-copy

Generate and A/B test Google Ads copy. Use when asked to write ad copy, headlines, descriptions, create ad variants, test ad messaging, improve CTR, or generate RSA (Responsive Search Ad) components. Trigger on "ad copy", "write ads", "headlines", "descriptions", "RSA", "responsive search ad", "ad text", "ad…

nowork-studio/notfair-plugin · 121 tokens