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 webaudio-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/webaudio-review)<a href="https://agentmods.dev/skills/kunitoki/sonic-skills/webaudio-review"><img src="https://agentmods.dev/badge/skills/kunitoki/sonic-skills/webaudio-review.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 5.1 | $0.00099 | $0.00989 |
| Opus 5 | $0.00049 | $0.00495 |
| Sonnet 5 | $0.00020 | $0.00198 |
| Haiku 4.5 | $0.00010 | $0.00099 |
Grade A, and why
webaudio-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 8d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Audio API Safety Review
Note — JS realtime model differs from native: JavaScript allocation does not look like
malloc, but it still creates garbage-collector work and can introduce render-thread jitter. The same cardinal rule applies: avoid allocations and blocking operations insideprocess().Invoke
audio-dsp-reviewconcepts (no allocations, no blocking) adapted for JavaScript: replace "mutex" with "GC pause" and "malloc" with "object/array creation".
Step 1 — Identify the architecture
Determine which Web Audio pattern is in use before scanning:
| Pattern | Where audio runs | Risk level |
|---|---|---|
AudioWorkletProcessor subclass |
Dedicated worklet thread | Medium — GC and message overhead |
ScriptProcessorNode |
Main thread | High — deprecated; blocks UI |
Main-thread AudioContext only |
Main thread | Low — standard graph |
OfflineAudioContext |
Offline render | Low — no real-time deadline |
Step 2 — Scan for violations
| Violation | Location | Risk |
|---|---|---|
Using ScriptProcessorNode |
Anywhere | Deprecated; runs on main thread → dropouts under UI load |
new Float32Array(...) inside process() |
AudioWorkletProcessor.process() |
GC allocation → potential pause during render |
Creating objects/arrays/closures inside process() |
AudioWorkletProcessor.process() |
GC pressure → jitter |
port.postMessage() every process() block |
AudioWorkletProcessor |
High overhead; batch updates or use SharedArrayBuffer |
Accessing window, document, or DOM from worklet |
process() or worklet scope |
Worklet thread has no DOM access — throws ReferenceError |
Importing non-worklet-safe modules in addModule() |
Worklet module file | DOM APIs throw; do network/file loading on the main thread and pass data in |
| Not handling autoplay policy | AudioContext creation |
Context starts suspended; must resume on user gesture |
SharedArrayBuffer comms without integer Atomics protocol |
Worklet ↔ main comms | Race-prone shared state — Atomics works on integer typed arrays, not Float32Array |
Changing AudioNode graph from worklet thread |
process() |
connect()/disconnect() are main-thread-only |
| Assuming a hardcoded render quantum in loops/buffers | process() |
Spec and browsers use 128-frame quanta today, but code should use output[channel].length |
Forgetting await audioContext.resume() |
After user gesture handler | Stays suspended; no audio output |
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.
- 8d ago First seen · 84 lines · 99 tokens per session scan A 60f3b2342635
webaudio-review is a skill published in the GitHub repository kunitoki/sonic-skills (19 stars, last pushed 3mo ago), licensed Unlicense. It adds 99 tokens to every session and 989 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
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".
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…
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-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…
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.