studio-project-scaffold

studio-project-scaffold is a skill for Codex from hoatv2211/GameStudio-CodexKIT. It costs 85 tokens per session (1,764 once invoked), scanned A, original, MIT.

A setup guide for adding project-local governance and agent-workflow files to a new or inherited game repository. It can create items such as AGENTS.md, HANDOFF.md, project profiles, subsystem ownership records, and backup or overlay plans.

In plain words
What is it for?
Use it when bootstrapping a game repository, adopting a legacy project, or preparing a report and merge plan for missing project governance.
Why use it?
It gives a project a shared structure for ownership, evidence, handoffs, and safe multi-session work. It also helps avoid overwriting governance that is already in place.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md; mentions Codex.

Good fit Use it when bootstrapping a game repository, adopting a legacy project, or preparing a report and merge plan for missing project governance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hoatv2211/gamestudio-codexkit/studio-project-scaffold
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 hoatv2211/GameStudio-CodexKIT --skill studio-project-scaffold
Clone the repo
git clone --depth 1 https://github.com/hoatv2211/GameStudio-CodexKIT

Made for: 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 studio-project-scaffold

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoatv2211/gamestudio-codexkit/studio-project-scaffold.svg)](https://agentmods.dev/skills/hoatv2211/gamestudio-codexkit/studio-project-scaffold)
Your own site
<a href="https://agentmods.dev/skills/hoatv2211/gamestudio-codexkit/studio-project-scaffold"><img src="https://agentmods.dev/badge/skills/hoatv2211/gamestudio-codexkit/studio-project-scaffold.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,764 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 $0.00085 $0.01764
Opus 5 $0.00043 $0.00882
Sonnet 5 $0.00017 $0.00353
Haiku 4.5 $0.00009 $0.00176

Measured today against content hash 13effe3ccc93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

studio-project-scaffold 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 10 executable files (scripts/agent_overlay.py, scripts/code_intelligence.py, scripts/codegraph_adapter.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.

skills/studio-project-scaffold/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Studio Project Scaffold

Overview

Create the minimum project-local governance, project profile, routing references, and agent-role overlay needed for safe multi-session work while preserving existing instructions, configuration, skills, and agents.

Newly generated profiles include optional studio_experience defaults for role, mode, and enabled intents. These defaults affect routing presentation only. Use gamestudio guide for a report-only Golden Path packet; gamestudio init --apply remains a separate reviewed mutation.

When to use

Use for a new game repository, an inherited legacy project without agent governance, or a project that needs standardized ownership, evidence labels, and handoff state.

When NOT to use

Do not overwrite a mature project-local .agents/ system, existing AGENTS.md, HANDOFF.md, or skills. Generate a report and merge plan instead.

Required inputs and context discovery

Collect workspace root, nested Git roots, Git state, existing governance files, Unity markers, server projects, Lua/data trees, database inputs, generated, cache, vendor, and excluded paths, project-local skill IDs, agent files, and .codex/config.toml state.

Safety and risk level

Scaffolding and the per-project adapter are medium-risk because they write governance and agent files. Run report-only first, preserve every existing file by default, and never mutate external projects during kit tests.

Workflow

  1. Scan structure read-only and detect Unity, server, Lua, database, tooling, and generated subsystems. Completion criterion: detected subsystems and unknown areas are reported.
  2. Inventory existing AGENTS.md, HANDOFF.md, .agents/, local skills, and ignore rules. Completion criterion: every existing governance artifact is marked preserve, merge, or BLOCKED.
  3. Render the minimum scaffold with evidence, ownership, repeated-work tooling, mutation, generated-file, no-touch rules, project profile, workspace map, validation matrix, and adapter references. Completion criterion: scaffold-report.json lists exact proposed and preserved scaffold files without writes.
  4. Run the per-project adapter report-only first. Review plan_digest, proposed planned paths, collisions, activated_roles, scope_review, preserved paths, and the action/hash details under mutation_report.operations. Broad resolved capability intersections are advisory; only out-of-scope or duplicate exact active write assignments block orchestration. Completion criterion: the reviewed adapter report identifies every proposed write and collision without mutation.
  5. Apply only that reviewed adapter plan with a named reviewer, a disjoint project-local backup root, and the approved plan digest. Generate and review a new report when the digest is stale. Completion criterion: apply uses all three gates and returns its manifest and restore command.
  6. Materialize roles from packaged generic agent templates plus profile and inferred specialists under .codex/agents/, preserving an explicit project reasoning_effort over the template default. The generated .codex/agents.generated.toml file remains inert until manual merge, and the adapter leaves .codex/config.toml untouched. Completion criterion: unmanaged agents and active configuration remain preserved, and effective scopes are reviewed only after role resolution.
  7. Record per-file ownership hashes under .agents/registry.json, then run project-local validation and inspect the generated handoff snapshot. Completion criterion: scaffold output is parseable and unresolved runtime facts remain Unverified or BLOCKED.
  8. Run uninstall report-only first and review its plan_digest, proposed, preserved_drift, and remaining_owned paths. Apply only with a named reviewer, a disjoint backup root, and that matching digest. Use hash-safe uninstall: remove only files matching recorded ownership hashes. Preserve drift and return PARTIAL with preserved_drift and remaining_owned for manual recovery when safe cleanup cannot finish. Completion criterion: uninstall never deletes unmanaged or drifted project content and cannot bypass the approval gates.

Read the full file on GitHub · 97 lines

Files

What ships with it

38 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. today Changed · +2 lines 13effe3ccc93
  2. yesterday Changed c3d24c202a95
  3. 8d ago First seen · 95 lines · 85 tokens per session scan A 7a7b62874910

Subscribe to this mod's changes

studio-project-scaffold is a skill published in the GitHub repository hoatv2211/GameStudio-CodexKIT (3 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 1,764 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

deep-discovery

Use when the user asks for deep discovery, 100-question brainstorming, idea interrogation, architecture stress testing, strategy vetting, weakness finding, hole-poking, exhaustive exploration, planning or auditing Codex plugins or skills, or pre-commitment review of a design, plan, strategy, architecture, product…

forsonny/deep-discovery · 76 tokens

prewalk

Use when the user wants a coding task executed with a strong planner model first and a faster/cheaper executor model after the first successful implementation edit.

vivekascoder/codex-prewalk · 33 tokens

code-standards

C# coding standards and code review. Use when the user mentions coding standards or conventions, writing code to spec, defining standards for a project, cohesion and coupling, design pattern selection, or naming conventions, or wants a code review on the design and standards dimension.

tianzhiying/Unity-perf · 58 tokens

registry-broker-orchestrator

Use Registry Broker to discover and summon specialist agents for focused subtasks from inside Codex.

hashgraph-online/registry-broker-codex-plugin · 25 tokens

unity-performance

Unity performance optimization. Use when the user asks to optimize a class, view, function, folder or an entire module, or mentions stutter, lag, frame drops, low FPS, jank, overheating, battery drain, GC allocation, memory leaks, DrawCalls, batching, overdraw, slow loading, large build size, Profiler, PerfDog, or…

tianzhiying/Unity-perf · 102 tokens

sega

A playful, arcade-inspired interface for games — built on the VT323 pixel typeface, hard-edged 0px corners, chunky pill buttons that physically press into solid offset blocks.

bergside/awesome-design-skills · 39 tokens