Borrowing it
Nothing to install: this file belongs to vchelaru/FlatRedBall2. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vchelaru/FlatRedBall2/main/.claude/skills/orchestrator/SKILL.mdgit clone --depth 1 https://github.com/vchelaru/FlatRedBall2Wrote 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/vchelaru/flatredball2/orchestrator)<a href="https://agentmods.dev/skills/vchelaru/flatredball2/orchestrator"><img src="https://agentmods.dev/badge/skills/vchelaru/flatredball2/orchestrator/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.
<a href="https://agentmods.dev/skills/vchelaru/flatredball2/orchestrator"><img src="https://agentmods.dev/badge/skills/vchelaru/flatredball2/orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 68 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 70 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00062 | $0.03318 |
| Opus 5.5 | $0.00025 | $0.01327 |
| Sonnet 5.5 | $0.00012 | $0.00664 |
| Haiku 4.5 | $0.00006 | $0.00332 |
Grade A, and why
orchestrator 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Minigame Orchestrator
See
content-boundaryskill first. Orchestrated games must scaffold placeholder content files (TMX, Gum screens, coefficients JSON) and close with an explicit handoff telling the user which files to open in which tools. Do not hardcode levels, UI composition, or tunable values in C#.
Test the FlatRedBall2 engine's AI-usability by designing and implementing a small retro game, then reporting friction.
Critical constraint: Do NOT read existing samples (samples/), unit tests (tests/), or any game code outside src/ and the current project being built. The only resources available are: engine source code (src/), XML docs, skill files (frb-skills/ for game-dev skills, .claude/skills/ for engine-contributor skills), and templates (.claude/templates/). This applies to you AND to the sub-agent you delegate to. The whole point of this evaluation is to test whether the engine's docs and skills are sufficient — looking at other samples defeats the purpose.
Pipeline
Execute these steps in order. Do not skip any step.
Step 1: Pick a Game
Determine which starting condition applies:
A. User provided a game design — Accept it as-is and skip to Step 3. Do not re-design or second-guess it.
B. User specified a game name/title — Use that game and proceed to Step 2.
C. No input — Choose a random game from the Atari 2600 or NES era. Aim for variety — avoid games that are structurally identical to common genres (e.g., don't always pick platformers). Examples: Frogger, Asteroids, Breakout, Galaga, Pac-Man, Donkey Kong, Dig Dug, Missile Command, Centipede, Joust, Balloon Fight, Ice Climber, Excitebike, Burger Time, Q*bert, Spy Hunter, River Raid, Pitfall, Moon Patrol.
Do NOT pick a game that already has a sample in samples/. Check first. (If the user explicitly requested a re-do of an existing game, delete the old project directory first.)
Complexity Levels
Default is Complexity 2 unless the user requests otherwise.
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.
- 1mo ago Changed bbf0625fc401
- 1mo ago First seen · 235 lines · 62 tokens per session scan A c57a4c43f117
orchestrator is a skill published in the GitHub repository vchelaru/FlatRedBall2 (15 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 3,318 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 2026-09-04.
Other skills, from other repositories
playtest-report
Structured playtest report template, or turn existing playtest notes into structured feedback.
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.