gsp-subagent-build-loop

gsp-subagent-build-loop is a skill for Claude Code, Codex from mike007jd/game-superpowers. It costs 28 tokens per session (345 once invoked), scanned A, original, MIT.

A development workflow that gives each meaningful game task to a builder, a reviewer, and a verifier in sequence. A verifier checks whether the result is playable and meets the intended requirements.

In plain words
What is it for?
Use it to build game features in reviewed slices, repeat work after failed checks, and safely divide separate areas such as gameplay, menus, and feedback.
Why use it?
It catches implementation problems and playability issues before a task is considered finished, while avoiding conflicting changes from multiple builders.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to build game features in reviewed slices, repeat work after failed checks, and safely divide separate areas such as gameplay, menus, and feedback.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mike007jd/game-superpowers/gsp-subagent-build-loop
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 mike007jd/game-superpowers --skill gsp-subagent-build-loop
Clone the repo
git clone --depth 1 https://github.com/mike007jd/game-superpowers

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.

agentmods badge for gsp-subagent-build-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/mike007jd/game-superpowers/gsp-subagent-build-loop/github.svg)](https://agentmods.dev/skills/mike007jd/game-superpowers/gsp-subagent-build-loop)
Your own site
<a href="https://agentmods.dev/skills/mike007jd/game-superpowers/gsp-subagent-build-loop"><img src="https://agentmods.dev/badge/skills/mike007jd/game-superpowers/gsp-subagent-build-loop/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.

agentmods 80×15 button for gsp-subagent-build-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/mike007jd/game-superpowers/gsp-subagent-build-loop"><img src="https://agentmods.dev/badge/skills/mike007jd/game-superpowers/gsp-subagent-build-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 345 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 $0.00028 $0.00345
Opus 5 $0.00014 $0.00172
Sonnet 5 $0.00006 $0.00069
Haiku 4.5 $0.00003 $0.00034

Measured 9d ago against content hash 1444a83323b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gsp-subagent-build-loop 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 9d 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.

publish/clawhub/gsp-subagent-build-loop/SKILL.md · 38 lines

What it actually says

Game Subagent Build Loop

Goal

Turn a game build into a default multi-agent workflow: builder, reviewer, verifier. The goal is stronger and more stable output from one user prompt, not thrift.

Outputs

Follow the gsp-orchestrator output strategy:

  • inline (default): present subagent build loop plan in conversation.
  • minimal or full: write docs/game-studio/subagent-build-loop.md.

Default loop

For each meaningful build task or end-to-end slice:

  1. Dispatch a builder subagent to implement the slice.
  2. Dispatch a reviewer subagent using gsp-build-review.
  3. Dispatch a verifier subagent using gsp-playability-verifier.
  4. If review or verification fails, send the builder back with the concrete findings.
  5. Repeat until the slice is acceptable or the blocker should be surfaced to the user.

Parallel policy

Parallel builders are allowed only when ownership is disjoint. Examples: core loop vs HUD, feedback vs content pass, gameplay slice vs menus. Do not parallelize builders that fight over the same files or architectural choices.

Quality policy

  • benchmark and showcase builds should prefer this loop by default
  • greenfield polished-prototype work should usually prefer this loop
  • live-risky work may still use a tighter reviewer / verifier loop with smaller tasks

Important

Do not claim completion after the builder finishes. Review and verification are expected to find problems.

Files

What ships with it

5 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.

  1. 9d ago First seen · 38 lines · 28 tokens per session scan A 1444a83323b5

Subscribe to this mod's changes

gsp-subagent-build-loop is a skill published in the GitHub repository mike007jd/game-superpowers (12 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 345 once invoked, about $0.0001 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

prototype

Concept prototype — validate the core idea is worth designing before writing GDDs. Run right after /brainstorm and /setup-engine. Routes to HTML, Engine, or Paper path based on game type. Produces a throwaway build and a PROCEED/PIVOT/KILL verdict.

Donchitos/Claude-Code-Game-Studios · 61 tokens

review-all-gdds

Holistic cross-GDD consistency and game design review. Reads all system GDDs simultaneously and checks for contradictions between them, stale references, ownership conflicts, formula incompatibilities, and game design theory violations (dominant strategies, economic imbalance, cognitive overload, pillar drift). Run…

Donchitos/Claude-Code-Game-Studios · 73 tokens

setup-engine

Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.

Donchitos/Claude-Code-Game-Studios · 45 tokens

ux-design

Guided, section-by-section UX spec authoring for a screen, flow, or HUD. Reads game concept, player journey, and relevant GDDs to provide context-aware design guidance. Produces ux-spec.md (per screen/flow) or hud-design.md using the studio templates.

Donchitos/Claude-Code-Game-Studios · 61 tokens

asset-spec

Generate per-asset visual specifications and AI generation prompts from GDDs, level docs, or character profiles. Produces structured spec files and updates the master asset manifest. Run after art bible and GDD/level design are approved, before production begins.

Donchitos/Claude-Code-Game-Studios · 54 tokens

localize

Full localization pipeline: scan for hardcoded strings, extract and manage string tables, validate translations, generate translator briefings, run cultural/sensitivity review, manage VO localization, test RTL/platform requirements, enforce string freeze, and report coverage.

Donchitos/Claude-Code-Game-Studios · 50 tokens