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 agentmods add skills/alterlab-ieu/alterlab_gameforge/game-launchnpx skills add AlterLab-IEU/AlterLab_GameForge --skill game-launchgit clone --depth 1 https://github.com/AlterLab-IEU/AlterLab_GameForgeWrote 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-launch)<a href="https://agentmods.dev/skills/alterlab-ieu/alterlab_gameforge/game-launch"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab_gameforge/game-launch.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 | $0.00106 | $0.09366 |
| Opus 5 | $0.00053 | $0.04683 |
| Sonnet 5 | $0.00021 | $0.01873 |
| Haiku 4.5 | $0.00011 | $0.00937 |
Grade A, and why
game-launch 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 3d 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 — 610 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AlterLab GameForge -- Pre-Release Launch Pipeline
The distance between "done" and "launched" is longer than most teams expect. And the distance between "launched" and "sustained" is longer still. A game that is feature-complete, bug-free, and fun can still fail because the store page was not optimized, the press kit was missing, the age rating was not filed, or the day-one patch pipeline was not tested. Worse -- a game that launches perfectly can die in week two without a post-launch strategy.
Hades did not become a cultural phenomenon on launch day. It became one through 18 months of Early Access with a meticulously planned patch cadence. Stardew Valley did not stop at 1.0 -- ConcernedApe's free content updates built a community that still plays eight years later. This workflow covers both sides: the exhaustive pre-launch pipeline AND the post-launch operations that determine whether your game survives past the first week.
Purpose & Triggers
Invoke this workflow when:
- The game is entering the final milestone before release and a structured launch plan is needed
- A storefront submission deadline is approaching and the team needs to verify all requirements are met
- Marketing assets need to be prepared and coordinated across platforms
- Legal and compliance requirements (age ratings, privacy policies, licenses) need auditing
- The team needs a go/no-go framework for making the launch decision
- A soft launch or early access release is being planned (same process, adjusted scope)
- Post-launch support infrastructure needs to be established before launch day
Do NOT use this workflow when:
- The game is still in active development with significant features incomplete (finish building first)
- You are launching an internal playtest build (use
game-playtestinstead) - The game is a game jam submission with no commercial intent (streamline to just build validation)
Critical Rules
- Every phase is gated. Do not advance to the next phase until the current phase is signed off. Skipping a phase to save time is how launches implode. Vampire Survivors launched without a press kit and still succeeded -- but that was 2021 lightning in a bottle, not a replicable strategy.
- Storefronts are not optional. A store page that is missing screenshots, has a vague description, or uses the wrong tags will kill discoverability. The store page IS the game's first impression. Treat it as a design deliverable, not a checkbox.
- Legal compliance is not a suggestion. Missing an age rating or privacy policy can result in the game being pulled post-launch. This is a catastrophic outcome that is entirely preventable.
- Plan for failure. The launch plan must include a rollback strategy. If the answer to "what if launch goes wrong?" is "panic," your launch plan is incomplete.
- Day-one patches are expected, not shameful. Between going gold and launch day, new issues will be found. The question is not "will we need one?" but "how fast can we deploy one?"
- Launch day is day one, not the finish line. Dead Cells shipped its 1.0 and then delivered 6 major content updates over 4 years. Hades had 18 months of Early Access patches before 1.0. Your post-launch strategy matters as much as your pre-launch checklist.
- Reference
docs/game-design-theory.mdfor player psychology considerations in storefront presentation and first-time user experience.
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.
- 3d ago First seen · 610 lines · 106 tokens per session scan A 7f34cb59543c
game-launch is a skill published in the GitHub repository AlterLab-IEU/AlterLab_GameForge (34 stars, last pushed 5mo ago), licensed MIT. It adds 106 tokens to every session and 9,366 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
influence-psychology
Apply the seven principles of ethical persuasion (reciprocity, commitment, social proof, authority, liking, scarcity, unity) to product design, copy, and sales. Use when the user mentions "social proof", "persuasive copy", "why users dont convert", "ethical persuasion", "reciprocity", "scarcity tactics", "commitment…
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
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.
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…
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.