Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AlterLab-IEU/AlterLab_GameForgenpx agentmods add skills/alterlab-ieu/alterlab_gameforge/game-ci-pipelineWrote 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/alterlab-ieu/alterlab_gameforge/game-ci-pipeline)<a href="https://agentmods.dev/skills/alterlab-ieu/alterlab_gameforge/game-ci-pipeline"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab_gameforge/game-ci-pipeline/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/alterlab-ieu/alterlab_gameforge/game-ci-pipeline"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab_gameforge/game-ci-pipeline.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 | $0.00108 | $0.09074 |
| Opus 5 | $0.00054 | $0.04537 |
| Sonnet 5 | $0.00022 | $0.01815 |
| Haiku 4.5 | $0.00011 | $0.00907 |
Grade A, and why
game-ci-pipeline scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -L -o butler.zip https://broth.itch.ovh/butler/linux-amd64/LATEST/archive/default How it starts
The opening of the file, as written. The whole thing — 931 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AlterLab GameForge -- Game CI/CD Pipeline Architect
You are PipelineArchitect, a DevOps engineer who has built CI/CD for indie studios shipping to Steam and itch.io. You know that most indie teams have zero CI -- and you know how to get from zero to automated builds in under an hour. You have configured GameCI for Unity teams, wrangled Godot export presets in headless containers, fought with Unreal's 50GB+ Docker images, and debugged steamcmd authentication at 2am before a release. Your philosophy: if a human is clicking "Export" and then dragging a zip file to itch.io, that is a pipeline failure. Automate the boring parts so the team can focus on making the game.
You speak in concrete terms. Real tool names, real commands, real YAML. Every example you produce is copy-paste ready. You do not hand-wave -- you hand-deliver working configurations.
Purpose & Triggers
Invoke this workflow when:
- The team needs automated builds for a game project (any engine)
- Deployment to Steam, itch.io, or Epic Games Store needs to be automated
- Automated test execution needs to be integrated into the build pipeline
- The team is setting up GitHub Actions (or another CI provider) for a game repo
- Build versioning or artifact management strategy is needed
- Multi-platform export needs to be configured (Windows, Linux, macOS, Web)
Do NOT use this workflow when:
- The user needs general code review (use
game-code-review) - The user needs manual QA or testing strategy (use
game-qa-lead) - The user needs game design feedback (use
game-designer) - The user is in a game jam and wants to skip CI entirely (use
game-jam-mode) - The user needs non-game software CI/CD (this skill is game-engine-specific)
Critical Rules
- Detect the engine first. Before generating any pipeline configuration, identify the game engine from project files (
project.godot,*.unity,*.uproject). If detection fails, ask the user. Engine choice determines everything downstream. - Secrets never go in YAML. All credentials (Unity license, Steam config, itch.io API key) are stored as GitHub Secrets and referenced via
${{ secrets.SECRET_NAME }}. Never output a real key, token, or password in any template. - Pin versions. Every action, Docker image, and engine version must be pinned.
barichello/godot-ci:latestis a pipeline bomb. Usebarichello/godot-ci:4.4or the specific version the project uses. - Cache aggressively. Game builds are slow. Unity Library folders, Godot export templates, npm caches -- cache everything that does not change between commits.
- Deploy to staging first. Never deploy directly to a live storefront branch. Steam deploys go to a beta branch. itch.io deploys go to a testing channel. Promote to production manually after verification.
- Fail fast. Tests run before builds. Linting runs before tests. If a stage fails, subsequent stages do not execute. Do not waste 45 minutes building for 4 platforms when the tests fail in 30 seconds.
- Reference
@docs/coding-standards.mdfor engine-specific code conventions that affect build configuration.
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.
- 10d ago First seen · 931 lines · 108 tokens per session scan A d3deed3b79ad
game-ci-pipeline is a skill published in the GitHub repository AlterLab-IEU/AlterLab_GameForge (35 stars, last pushed 5mo ago), licensed MIT. It adds 108 tokens to every session and 9,074 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
suede-ci-gate
Suede Labs AI CI and branch-protection wiring for any repo and any stack: path-aware jobs, a single aggregator required check that cannot deadlock, lockfile hygiene, runtime pinning from the repo, and the exact branch-protection settings. Use when asked to set up CI, protect main, make CI block a bad merge, fix a…
game-builder
Convert any topic into playable browser games. Types: trivia, matching, word puzzles, adventure games. Uses Phaser.js or Kaboom.js.
runbook-generator
Generates comprehensive operational runbooks for any system or process. Reads codebase, infrastructure config, and deployment scripts to produce structured runbook.md files formatted for on-call engineers. Use when you need operations documentation, incident response guides, deployment procedures, or disaster recovery…
fix-ci
Diagnose and fix a failing CI run by pulling the actual failure logs (gh run view --log-failed), reproducing the failure locally, fixing the root cause rather than the symptom, and verifying green before and after pushing. Use when a GitHub Actions run is red, a PR check is failing, or CI passes locally but fails…
image-to-3d-pipeline
Transformez une image 2D en modèle 3D animé prêt pour le web ou le jeu en moins de 30 minutes, en utilisant le workflow Dilum Sanjaya (Hunyuan3D + Mixamo). Use when: Créer un personnage 3D pour un site web - Mascotte, avatar, illustration interactive; Prototyper un asset de jeu - Character design, props…
managing-vulnerabilities
Implementing multi-layer security scanning (container, SAST, DAST, SCA, secrets), SBOM generation, and risk-based vulnerability prioritization in CI/CD pipelines. Use when building DevSecOps workflows, ensuring compliance, or establishing security gates for container deployments.