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 wvdsh/ai --skill wavedashgit clone --depth 1 https://github.com/wvdsh/aiWrote 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/wvdsh/ai/wavedash)<a href="https://agentmods.dev/skills/wvdsh/ai/wavedash"><img src="https://agentmods.dev/badge/skills/wvdsh/ai/wavedash/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/wvdsh/ai/wavedash"><img src="https://agentmods.dev/badge/skills/wvdsh/ai/wavedash.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 | $0.00063 | $0.00748 |
| Opus 5.5 | $0.00025 | $0.00299 |
| Sonnet 5.5 | $0.00013 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
wavedash 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wavedash
Use this skill to get a game from local project to tested, uploaded, and publishable on Wavedash. Official docs are canonical; this skill routes the agent to the right docs and highlights traps agents commonly miss.
Always do this
- Identify whether the user is starting from an existing game or from zero. If no game exists yet, create a small browser-playable game first.
- Identify the engine/framework, build command, output directory, and requested Wavedash features.
- If the Wavedash MCP server is available, call
wavedash_implementation_plannerbefore making architecture claims, selecting SDK features, or writing Wavedash integration code. Treat the planner's docs list and boundaries as the routing source for the next steps. - Read the relevant reference file before changing code or giving detailed instructions. Do not invent SDK methods, event names, constants, CLI flags, monetization rules, or content-policy exceptions.
- Prefer the CLI for local testing and scripted upload/publish workflows.
- Publish only when the user explicitly asks to make a build live.
- Use
WAVEDASH_TOKENin CI, cloud-agent, or other headless automation contexts, and pass--jsonwhere a command supports it (auth status,team list,project list,achievement list).
Routing
| User task | Read first |
|---|---|
| Start a new game from zero, scaffold a browser game, choose a framework | references/project-start.md |
| Install CLI, authenticate, initialize, test locally, upload, publish | references/cli.md |
| Add or fix SDK calls, player identity, load lifecycle, events | references/sdk.md |
| Add multiplayer, lobbies, networking | references/sdk.md |
| Add achievements, stats, leaderboards, cloud saves, UGC, paid content | references/sdk.md |
| Prepare store page, metadata, monetization, content policy, launch checklist | references/publishing.md |
| Fix launch-quality issues like shader stutter, Escape key, audio, memory | references/game-quality.md |
| Determine engine-specific build/export steps | references/engines.md |
| Need all docs URLs or raw Markdown links | references/docs-map.md |
What ships with it
7 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.
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 · +1 lines d06797fe4dcb
- 1mo ago First seen · 58 lines · 63 tokens per session scan A 6e353b187b5a
wavedash is a skill published in the GitHub repository wvdsh/ai (2 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 748 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
authoring-scouts
Write, edit, and adapt PostHog Signals scouts: scheduled agents that scan a project and report findings. Use to change a canonical scout's scope, thresholds, schedule, or dry-run settings; add a scout for an uncovered surface; record structured output from scheduled LLM scoring; or give feedback through notes. Covers…
exploring-scouts
How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox. Use when a user wants to understand what scouts they have, how each one is behaving, and whether the fleet is actually working. Covers surveying the fleet and its schedules…
inbox-exploration
Explore PostHog's Inbox and act on what it surfaces — the place where signal reports cluster into actionable issues and trends. Use when the user asks "what's in my inbox?", "what should I look at?", "which reports are actionable?", "what's PostHog flagged recently?", asks about a specific report by ID or title, wants…
resolving-ingestion-warnings
Diagnoses and resolves PostHog ingestion warnings — problems recorded while ingesting events (dropped events, rejected person merges, oversized payloads, invalid data). Use when a user asks why events are missing, dropped, or undercounted, why identify/alias calls don't work or accounts stay duplicated, why person or…
creating-online-evaluations
Author continuously-running online evaluations in PostHog AI observability, grounded in real failure modes you've identified. Use when the user wants evaluations that automatically score new generations or whole traces going forward — "create an eval to catch X", "continuously check that responses do Y", "turn these…
feature-usage-feed
Set up an LLM-judge evaluation that extracts canonical use cases for a PostHog feature at scale and streams the results to a Slack channel as a live feed. Use when someone wants to understand how users are actually using a specific AI/LLM-powered feature in production — what they're investigating, what questions…