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 frabcd/codex-ai-game-studio --skill smoke-checkgit clone --depth 1 https://github.com/frabcd/codex-ai-game-studioWrote 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/frabcd/codex-ai-game-studio/smoke-check)<a href="https://agentmods.dev/skills/frabcd/codex-ai-game-studio/smoke-check"><img src="https://agentmods.dev/badge/skills/frabcd/codex-ai-game-studio/smoke-check/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/frabcd/codex-ai-game-studio/smoke-check"><img src="https://agentmods.dev/badge/skills/frabcd/codex-ai-game-studio/smoke-check.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 Memory Poisoning · line 246 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Excessive Agency · line 419 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 | $0.00061 | $0.04009 |
| Opus 5.5 | $0.00024 | $0.01604 |
| Sonnet 5.5 | $0.00012 | $0.00802 |
| Haiku 4.5 | $0.00006 | $0.00401 |
Grade A, and why
smoke-check 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 — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Port provenance: adapted from the pinned upstream source at
984023ddac0d5e27624f2baacde6105e45de375funder MIT; see the repository parity ledger for the exact path and blob.
Smoke Check
This skill is the gate between "implementation done" and "ready for QA hand-off". It runs the automated test suite, checks for test coverage gaps, batch-verifies critical paths with the developer, and produces a PASS/FAIL report.
The rule is simple: a build that fails smoke check does not go to QA. Handing a broken build to QA wastes their time and demoralises the team.
Output: production/qa/smoke-[date].md
Parse Arguments
Arguments can be combined: $ai-game-studio:smoke-check sprint --platform console
Base mode (first argument, default: sprint):
sprint— full smoke check against the current sprint's storiesquick— skip coverage scan (Phase 3) and Batch 3; use for rapid re-checks
Platform flag (--platform, default: none):
--platform pc— add PC-specific checks (keyboard, mouse, windowed mode)--platform console— add console-specific checks (gamepad, TV safe zones, platform certification requirements)--platform mobile— add mobile-specific checks (touch, portrait/landscape, battery/thermal behaviour)--platform all— add all platform variants; output per-platform verdict table
If --platform is provided, Phase 4 adds platform-specific batches and
Phase 5 outputs a per-platform verdict table in addition to the overall verdict.
Phase 1: Detect Test Setup
Before running anything, understand the environment:
-
Test framework check: verify
tests/directory exists. If it does not: "No test directory found attests/. Run$ai-game-studio:test-setupto scaffold the testing infrastructure, or create the directory manually if tests live elsewhere." Then stop. -
CI check: check whether
.github/workflows/contains a workflow file referencing tests. Note in the report whether CI is configured.
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.
- 1mo ago First seen · 425 lines · 61 tokens per session scan A d8e5a5fc1904
smoke-check is a skill published in the GitHub repository frabcd/codex-ai-game-studio (17 stars, last pushed 5d ago), licensed MIT. It adds 61 tokens to every session and 4,009 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 2026-09-03.
Other skills, from other repositories
scenario-godot-expert
Use when an agent drives Godot 4.7 on macOS or Windows for any task: headless --script jobs, --import, --check-only, command-line exports, GUT tests, windowed screenshots, the headless editor (-e) or an MCP server into a running editor; when a run hangs or fails silently, a capture is black, Godot 3 code breaks in…
scenario-unity-expert
Use when an agent drives Unity 6.3 (6000.3) on a Mac for any task: batch mode and -executeMethod jobs, a running editor (the user's GUI editor or a headless one), the Unity CLI and com.unity.pipeline, MCP servers, the Test Framework, command-line builds; when a batch run fails silently, 'Scripts have compiler errors'…
scenario-godot-gameplay
Use when building gameplay systems in Godot 4.7: enemy AI that patrols, chases and attacks, state machines, behavior trees (LimboAI), NavigationAgent3D pathfinding and avoidance for 100 to 1000 enemies, 'agents stack up' or 'path is empty', hitbox and hurtbox combat, fast bullets going through walls, save and load…
scenario-roblox-gameplay
Use when building Roblox gameplay systems: NPC or enemy AI that patrols, chases and attacks, state machines or behavior trees, 'NPC pathfinding stuck', 100 zombies lag the server, hitboxes, melee combos, M1 combat, 'hits register twice', raycasts, Spherecast, Shapecast, guns and projectiles, 'bullets go through…
game-qa
Verify a game with evidence on its selected target runtime. Launch the actual build and prove real rendering, input, the core loop, at least one designed outcome, restart, and explicit limitations without dressing subjective fun up as a certain verdict. Use for test a generated game, QA a game build, check whether the…
blender-asset-validation
Inspect and validate Blender assets technically and visually. Use for .blend, .glb, .gltf, .fbx, or .obj quality checks; topology and export review; evaluated triangle/material/hierarchy metrics; standardized multiview renders; fresh-import verification; or evidence-backed review of an agent-generated mesh.