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 skills add hoatv2211/GameStudio-CodexKIT --skill studio-agent-orchestrationgit clone --depth 1 https://github.com/hoatv2211/GameStudio-CodexKITWrote 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/hoatv2211/gamestudio-codexkit/studio-agent-orchestration)<a href="https://agentmods.dev/skills/hoatv2211/gamestudio-codexkit/studio-agent-orchestration"><img src="https://agentmods.dev/badge/skills/hoatv2211/gamestudio-codexkit/studio-agent-orchestration.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 5.1 | $0.00047 | $0.01059 |
| Opus 5 | $0.00023 | $0.00530 |
| Sonnet 5 | $0.00009 | $0.00212 |
| Haiku 4.5 | $0.00005 | $0.00106 |
Grade A, and why
studio-agent-orchestration 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.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Studio Agent Orchestration
Overview
Choose agent roles only where parallelism creates leverage. Keep the immediate critical path on the main thread and make every sidecar contract independently verifiable.
When to use
Use when two or more independent workstreams exist, repeated discovery can be partitioned, a stable slice needs independent verification, or a project profile declares a specialist role.
When NOT to use
Do not delegate small one-file work, immediate blockers, overlapping writes, shared unstable contracts, or tightly coupled edit-test iteration. Do not use a specialist outside its declared repository.
Required inputs and context discovery
Collect the workspace route, immediate critical-path action, candidate workstreams, resolved profile and inferred role templates, capability scopes, exact active file assignments, read-only scopes, expected outputs, concurrency limit, available role definitions, and validation requirements.
Safety and risk level
Planning is read-only. Agent role selection never expands mutation permissions. Investigator and review lanes remain read-only; implementers own exact disjoint paths; verifiers may write only normal test/build artifacts.
Workflow
- Identify the immediate critical-path action and keep it on the main thread. Completion criterion: no sidecar blocks the next local action.
- Resolve profile specialists, inferred specialists, and canonical templates before reviewing effective owned scopes. Record broad scope intersections as
capability-overlap; they describe what roles can own and do not by themselves block activation. Completion criterion: the review distinguishes effective capability patterns from exact files assigned in the current work packet. - Reject an active assignment outside its role's effective scope or any exact file assigned to more than one simultaneous writer. Also reject generated targets or unstable shared interfaces that lack one owner. Completion criterion: every concurrent writer has a disjoint exact write set, while disjoint assignments remain allowed even when role capabilities overlap.
- Select the narrowest role: investigator for ownership discovery, implementer for bounded writes, verifier for independent checks, or a profile-declared specialist for difficult domain work. Completion criterion: role choice is justified by scope rather than prestige.
- Bound concurrency by project profile and available independent work. Completion criterion: concurrency never exceeds three and may be zero.
- Give each sidecar ownership, do-not-touch scope, expected output, and verification contract. Completion criterion: sidecars cannot create child agents and the main thread owns integration.
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.
- today Changed · +5 lines 3bcb48c44b93
- 7d ago First seen · 79 lines · 47 tokens per session scan A a630a02756d1
studio-agent-orchestration is a skill published in the GitHub repository hoatv2211/GameStudio-CodexKIT (3 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 1,059 once invoked, about $0.0002 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
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…
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.
registry-broker-orchestrator
Use Registry Broker to discover and summon specialist agents for focused subtasks from inside Codex.
codex-sdd:customize
Guide for injecting custom MCP tools, skills, and hook points into the OpenSpec workflow for team-specific processes.
codex-sdd:archive
Preserve change artifacts (proposal, design, tasks) into structured archive and update knowledge base. Final phase of OpenSpec workflow.
codex-sdd:plan
Create design.md with technical architecture and tasks.md with executable breakdown from an approved proposal. Second phase of OpenSpec workflow.