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 DanMcInerney/orchflows --skill 3d-browser-gamegit clone --depth 1 https://github.com/DanMcInerney/orchflowsWrote 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/danmcinerney/orchflows/3d-browser-game)<a href="https://agentmods.dev/skills/danmcinerney/orchflows/3d-browser-game"><img src="https://agentmods.dev/badge/skills/danmcinerney/orchflows/3d-browser-game/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/danmcinerney/orchflows/3d-browser-game"><img src="https://agentmods.dev/badge/skills/danmcinerney/orchflows/3d-browser-game.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00029 | $0.00782 |
| Opus 5 | $0.00015 | $0.00391 |
| Sonnet 5 | $0.00006 | $0.00156 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
3d-browser-game 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.
What it actually says
Require: one brief, a git-backed workspace, and explicit
amendments. The brief and amendments are product authority.
Open one frame and retain its returned frame identity:
tickets.py frame-open <run> --goal-file <program-goal> --workflow 3d-browser-game
Research and design. Open the discovery helper under the frame. It audits
promises, runs independent research lanes, records capability gaps and
user-only questions verbatim, and freezes the core concept, controls, state
model, traceability, rubric, capture matrix, and performance plan before code.
tickets.py frame-open <run> --goal-file <discovery-goal> --parent <frame> --workflow discovery
tickets.py frame-close <run> <discovery-frame> --done <discovery-check>
Core implementation. Open playable-increment with the frozen design.
Its I0, I1, and I2 candidates use Three.js primitives or functional
placeholders, ordinary input, readable feedback, and scoped QA/play evidence;
each carries its fixed revision before the next increment.
tickets.py frame-open <run> --goal-file <increment-goal> --parent <frame> --workflow playable-increment
tickets.py frame-close <run> <increment-frame> --done <increment-check>
Open gameplay-gate over the fixed I2 revision. It separates QA, adaptive
play, and maker-independent judgment. Repairs preserve the complaint ledger
and fixed criteria; a bound or unavailable capability returns the best
identity and unresolved evidence. Redesign names its invalidated descendants.
tickets.py frame-open <run> --goal-file <core-gate-goal> --parent <frame> --workflow gameplay-gate
tickets.py frame-close <run> <core-gate-frame> --done <core-gate-check>
Production and final acceptance. Only an accepted core identity freezes
mechanics, collision, camera, controls, and timing. Generate and inspect
concept art, then open blender-asset jobs for source, render, export,
manifest, GLB, and runtime evidence. Gameplay-changing art invalidates the
affected core verdict. Integrate assets and open final-acceptance for play,
captures, performance cells, and independent judgment. Repair cycles preserve
complaint IDs, causes, contrary evidence, and resume state.
tickets.py frame-open <run> --goal-file <asset-goal> --parent <frame> --workflow blender-asset
tickets.py frame-close <run> <asset-frame> --done <asset-check>
tickets.py frame-open <run> --goal-file <final-goal> --parent <frame> --workflow final-acceptance
tickets.py frame-close <run> <final-frame> --done <final-check>
Close from outside every child only after all children return:
tickets.py frame-close <run> <frame> --done <outside-probe>
Never invent a promise, settle a user-only question silently, fabricate play
or performance, let art bypass core acceptance, relax a score floor, erase a
complaint, mix package revisions, or claim gaps: [] without observed gate
and outside-probe evidence.
Return: tickets.py frame-close <run> <frame> --done <outside-probe>, carrying
the accepted artifact: git:<full-commit-id>, evidence-index and gate
identities, outside-probe reading, or the best fixed revision and exact resume
state with every unresolved gap declared.
What ships with it
60 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.
- package-lock.json 3.7 KB
- package.json 293 B
- references/asset-manifest.schema.json 8.5 KB
- references/blender-job.schema.json 8.6 KB
- references/blender-probe-job.json 3.2 KB
- references/browser-game-checkpoint.schema.json 7.5 KB
- references/browser-game-instance-fixtures.json 7.7 KB
- references/browser-game-intake-policy.json 10.0 KB
- references/browser-game-program-record.schema.json 38 KB
- references/capture-matrix.schema.json 1.9 KB
- references/common.schema.json 3.0 KB
- references/core-rubric.md 2.7 KB
- references/evidence-index.schema.json 4.7 KB
- references/final-rubric.md 3.2 KB
- references/gate-verdict.schema.json 7.8 KB
- references/lineage.schema.json 2.9 KB
- references/outside-probe-report.md 3.0 KB
- references/outside-probe.schema.json 5.3 KB
- references/performance-cell.schema.json 14 KB
- references/performance-native-repair-2026-09-06.md 5.0 KB
- references/performance-plan.schema.json 3.2 KB
- references/performance-qualification/canvas-stall-other-layer.json 13 KB
- references/performance-qualification/continuous-animation.json 13 KB
- references/performance-qualification/deliberate-stall.json 13 KB
- references/performance-qualification/README.md 6.5 KB
- references/performance-qualification/static-idle.json 1.0 KB
- references/performance-qualification/threejs-default-renderer.cell.json 855 B
- references/performance-qualification/threejs-default-renderer.html 941 B
- references/performance-qualification/threejs-moving-mesh.cell.json 879 B
- references/performance-qualification/threejs-moving-mesh.html 1.6 KB
- references/performance-qualification/threejs-stalled-canvas-other-layer.html 1.5 KB
- references/play-session.schema.json 5.0 KB
- references/probe_generator.py 6.0 KB runs code
- references/run-record.schema.json 8.5 KB
- references/traceability.schema.json 4.5 KB
- scripts/_common.mjs 6.3 KB runs code
- scripts/asset_validation.mjs 30 KB runs code
- scripts/blender_asset_job.py 37 KB runs code
- scripts/blender_job_runner.py 57 KB runs code
- scripts/browser_harness.mjs 19 KB runs code
- scripts/capability_probe.py 5.6 KB runs code
- scripts/gate_lineage.mjs 29 KB runs code
- scripts/outside_build.mjs 11 KB runs code
- scripts/outside_harness.mjs 1.6 KB runs code
- scripts/outside_probe.mjs 37 KB runs code
- scripts/outside_server.mjs 6.2 KB runs code
- scripts/performance_collect.mjs 73 KB runs code
- scripts/trace_frames.mjs 52 KB runs code
- scripts/validate_evidence.mjs 74 KB runs code
- skills/blender-bpy/SKILL.md 2.1 KB
- standards/blender-game-asset/STANDARD.md 1.4 KB
- standards/browser-game-3d-asset/STANDARD.md 1.4 KB
- standards/browser-game-interface/STANDARD.md 1.3 KB
- standards/browser-game-playtest/STANDARD.md 1.3 KB
- standards/threejs-browser-game/STANDARD.md 1.4 KB
- tools.txt 286 B
- workflows/blender-asset/SKILL.md 2.4 KB
- workflows/brief-intake/SKILL.md 4.9 KB
- workflows/brief-intake/traceability.json 8.9 KB
- workflows/discovery/SKILL.md 3.0 KB
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 · -4 lines dc27f9602972
- yesterday First seen · 70 lines · 29 tokens per session scan A 395e10f651fd
3d-browser-game is a skill published in the GitHub repository DanMcInerney/orchflows (53 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 782 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 2026-09-10.
Other skills, from other repositories
browser-a2d9b0b0
A browser gamepad skill for detecting connected controllers and reading their buttons and analogue sticks.
bg3-steam-launcher
Launch Baldur's Gate 3 through Steam on macOS and load saved games using macos-automator and peekaboo MCP servers. Designed for testing bg3se-macos (Script Extender) development. Use when: (1) launching BG3 from Steam, (2) loading a BG3 saved game, (3) testing SE mod injection, (4) user asks to "start BG3", "load my…
multiplatform-conversion
Converting a single-target FlatRedBall2 desktop sample into a dual-target desktop + KNI BlazorGL (Blazor WebAssembly / browser) project. Use when the user mentions web deployment, browser/WASM/itch.io targets, KNI, or asks to add web support to an existing game. Assumes you already have a working desktop sample — see…
agent-casino-gambling
Interact with MoltCasino - a 3D Vegas-style casino built for AI agents.
webg-spec-to-goal
Convert a web game idea (even a vague one like "build a Raiden-type game" or "make a card game") into a complete Codex /goal-ready Phaser 3 project — runnable scaffold, goals-plan.md, and all goal folders (GOAL.md + VERIFY.md + PROGRESS.md) generated at once. Auto-detects genre (shoot-em-up, card game, platformer…
web-game-development
Implement and optimize browser games using Phaser, Three.js, React Three Fiber, Babylon.js, or PlayCanvas with responsive input, asset loading, rendering, and browser playtests. Use for JavaScript or TypeScript game projects.