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 kunitoki/sonic-skills --skill game-audio-reviewgit clone --depth 1 https://github.com/kunitoki/sonic-skillsWrote 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/kunitoki/sonic-skills/game-audio-review)<a href="https://agentmods.dev/skills/kunitoki/sonic-skills/game-audio-review"><img src="https://agentmods.dev/badge/skills/kunitoki/sonic-skills/game-audio-review/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/kunitoki/sonic-skills/game-audio-review"><img src="https://agentmods.dev/badge/skills/kunitoki/sonic-skills/game-audio-review.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 | $0.00123 | $0.01010 |
| Opus 5 | $0.00062 | $0.00505 |
| Sonnet 5 | $0.00025 | $0.00202 |
| Haiku 4.5 | $0.00012 | $0.00101 |
Grade A, and why
game-audio-review 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 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.
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Audio Middleware Review
Middleware callbacks share all realtime constraints of native audio, plus middleware-specific memory, threading, and parameter rules.
Step 0 — Run universal checks first
Invoke audio-dsp-review and audio-numerics-review before this skill. This skill adds
middleware-specific checks on top; it does not replace realtime-safety or numerics reviews.
Step 1 — Identify the integration type
| Type | Entry point | Key concerns |
|---|---|---|
| Wwise plugin | AkPluginInfo + Execute() |
Memory via AkAlloc, thread model per platform |
| FMOD DSP effect | FMOD_DSP_DESCRIPTION + process callback |
FMOD_MEMORY_ALLOC, must not block |
| Unreal MetaSounds | IMetaSoundSource, GetNextBuffer |
GameThread vs AudioThread ownership |
| Custom engine integration | Engine audio callback | Platform-specific thread model and priorities |
Step 2 — Scan for violations
| Violation | Where | Risk |
|---|---|---|
| Allocating from any heap inside the audio callback | plugin Execute/process |
Realtime violation; middleware allocators are for setup/teardown, not per-buffer allocation |
| Blocking I/O from audio callback | Execute/process |
Xrun / dropout |
| Accessing game engine state from audio thread | Execute/process |
Not thread-safe; data race or stale read |
| Event or parameter changes without thread-safe channel | game loop → audio | Data race on shared state |
| DSP plugin not handling bypass correctly | Execute/process |
Incorrect audio output in bypass mode |
| Not respecting channel count negotiation | plugin init | Buffer overread / underwrite |
Missing AK_OPTIMIZED guard around debug code |
any plugin code | Debug I/O included in shipping build |
| Wwise RTPC not clamped before use | parameter read | Out-of-range value fed to DSP; clipping or NaN |
| FMOD parameter index used as a magic number | parameter read | Wrong value applied after descriptor edits; use a shared enum tied to paramdesc order |
Unreal: accessing UAudioComponent from AudioThread |
GetNextBuffer |
GameThread-only object; crashes on non-GameThread |
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.
- 10d ago First seen · 88 lines · 123 tokens per session scan A 64c7995d7804
game-audio-review is a skill published in the GitHub repository kunitoki/sonic-skills (19 stars, last pushed 3mo ago), licensed Unlicense. It adds 123 tokens to every session and 1,010 once invoked, about $0.0006 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
audit-pr
Audit a whole PR against the delivery contract and return MERGE-READY or evidenced blockers with the full URL. Consumes the current review-change REVIEW-PASS receipt instead of re-running review axes; posts a SHA-bound ready comment; never edits or merges. Triggers: "audit-pr", "is this PR ready", "merge gate".
fold-findings
Repair persisted fix-now findings in compatible atomic batches: root-cause fixes, green gate, commit/push, and per-row folded: yes updates. Never reclassify or substitute backlog notes. Triggers: "fold-findings", "fix the review findings", "repair audit blockers".
review-change
Review a change with only applicable internal axes, classify every finding, persist fix-now work, and return one evidence-backed decision. Findings only; --adversarial N uses isolated reviewers; --synthesize fuses supplied reviewer tables. Triggers: "review-change", "review this change", "adversarial review".
review-plan
Independent read-only review of a frozen Engineering plan before execution, in a context that did not cut it: feature or fix snapshot, obligation ledger sweep, phase and validator checks. Returns only PLAN-REVIEW-PASS or PLAN-REVIEW-FAIL with a snapshot-bound receipt (a product-intent gap is PLAN-REVIEW-FAIL with…
review-perf
Internal performance review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks the changed paths for algorithmic and resource regressions: N+1s, hot-path allocations, asset weight, and leaks. Findings only; never edits code.
review-code
Internal correctness + simplification review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks correctness, error handling, duplication, dead code, and simplification opportunities against the project's own conventions. Findings only; never edits…