Borrowing it
Nothing to install: this file belongs to silver-rain-dev/sk-wwise-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/silver-rain-dev/sk-wwise-mcp/main/.claude/skills/eval-setup/SKILL.mdgit clone --depth 1 https://github.com/silver-rain-dev/sk-wwise-mcpWrote 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/silver-rain-dev/sk-wwise-mcp/eval-setup)<a href="https://agentmods.dev/skills/silver-rain-dev/sk-wwise-mcp/eval-setup"><img src="https://agentmods.dev/badge/skills/silver-rain-dev/sk-wwise-mcp/eval-setup/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/silver-rain-dev/sk-wwise-mcp/eval-setup"><img src="https://agentmods.dev/badge/skills/silver-rain-dev/sk-wwise-mcp/eval-setup.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 | $0.00022 | $0.00617 |
| Opus 5.5 | $0.00009 | $0.00247 |
| Sonnet 5.5 | $0.00004 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
eval-setup 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 2mo 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ TEST SETUP ONLY. Do NOT use for production. This creates a throwaway Wwise project and populates it with test objects.
Execute these steps in order using MCP tools. Stop if any step fails.
Step 1: Create test project and start headless WAAPI
- Use
cli_create_new_projectto create a fresh project attests/eval/EvalTestProject/EvalTestProject.wproj - Use
cli_start_waapi_serverto launch a headless WAAPI server with that project - Wait 5 seconds, then ping Wwise to confirm connection
- Get project info to verify the project loaded
Step 2: Create Actor-Mixer hierarchy
Under \Containers\Default Work Unit, create:
- ActorMixer "EvalTest_SFX"
- RandomSequenceContainer "Footsteps" (set Volume to -6.0)
- Sound "Footstep_01"
- Sound "Footstep_02"
- SwitchContainer "Weapons"
- Sound "Sword_Hit"
- Sound "Bow_Shot"
- ActorMixer "Ambience"
- Sound "Forest_Loop"
- Sound "Wind_Loop"
- RandomSequenceContainer "Footsteps" (set Volume to -6.0)
Step 3: Create Events
Under \Events\Default Work Unit, create:
- Folder "EvalTest_Events"
- Event "Play_Footstep"
- Event "Play_Sword"
- Event "Play_Ambience"
Step 4: Create States and Switches
- Under
\States\Default Work Unit: StateGroup "PlayerHealth" with States: "Alive", "Low", "Dead" - Under
\Switches\Default Work Unit: SwitchGroup "Surface" with Switches: "Grass", "Stone", "Wood"
Step 5: Set references
- Set Weapons SwitchContainer to use SwitchGroup "Surface"
- Assign Sword_Hit to "Grass" switch
- Assign Bow_Shot to "Stone" switch
Step 6: Write setup manifest
Write the WAAPI server PID, project path, and created object paths to tests/eval/setup_manifest.json:
{
"project_path": "tests/eval/EvalTestProject/EvalTestProject.wproj",
"waapi_pid": <PID from cli_start_waapi_server>,
"objects": {
"actor_mixer": "\\Containers\\Default Work Unit\\EvalTest_SFX",
"footsteps": "\\Containers\\Default Work Unit\\EvalTest_SFX\\Footsteps",
"weapons": "\\Containers\\Default Work Unit\\EvalTest_SFX\\Weapons",
"events_folder": "\\Events\\Default Work Unit\\EvalTest_Events"
}
}
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.
- 2mo ago First seen · 72 lines · 22 tokens per session scan A 62e45c1a77b4
eval-setup is a skill published in the GitHub repository silver-rain-dev/sk-wwise-mcp (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 617 once invoked, about $0.0001 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.
eval-setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| eval-setupsilver-rain-dev/sk-wwise-mcp | Skill | 5 | 1mo ago | Apache-2.0 | A | 22 | Claude Code |
| opik-diagnosecomet-ml/opik-mcp | Skill | 225 | 9d ago | Apache-2.0 | A | 187 | Claude Code |
| ue-mcp-epic-routingdb-lyon/ue-mcp | Skill | 476 | yesterday | MIT | A | 81 | Claude Code, Codex |
| qa-knowledgegriddynamics/rosetta | Skill | 370 | yesterday | Apache-2.0 | A | 32 | Claude Code, Codex |
| apitapn1byn1kt/apitap | Skill | 131 | 17d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| frontmcp-setupagentfront/frontmcp | Skill | 148 | yesterday | Apache-2.0 | A | 176 | Claude Code, Codex |
| x-use-reviewihuzaifashoukat/x-use | Skill | 181 | 4d ago | MIT | A | 56 | Claude Code |