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 juce-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/juce-review)<a href="https://agentmods.dev/skills/kunitoki/sonic-skills/juce-review"><img src="https://agentmods.dev/badge/skills/kunitoki/sonic-skills/juce-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/juce-review"><img src="https://agentmods.dev/badge/skills/kunitoki/sonic-skills/juce-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 | $0.00115 | $0.01146 |
| Opus 5 | $0.00057 | $0.00573 |
| Sonnet 5 | $0.00023 | $0.00229 |
| Haiku 4.5 | $0.00012 | $0.00115 |
Grade A, and why
juce-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 9d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JUCE Audio Plugin Review
JUCE abstractions hide thread boundaries — always trace which thread each piece of code runs on before declaring it safe.
Step 0 — Run universal checks first
Invoke audio-dsp-review and audio-numerics-review before this skill. This skill adds JUCE-specific checks on top; it does not replace realtime-safety or numerics reviews.
Step 1 — Identify plugin structure
Locate the three core classes and their thread ownership:
AudioProcessor— audio thread ownsprocessBlock; message thread owns everything elseAudioProcessorEditor— message thread only; never call from audio threadAudioProcessorValueTreeState— parameter tree lives on message thread; audio thread must usegetRawParameterValue()raw pointers only
Step 2 — Scan for JUCE violations
| Violation | Where to look | Risk |
|---|---|---|
juce::String construction/concatenation |
processBlock, DSP helpers |
May allocate and may touch shared string/logging machinery; realtime unsafe |
DBG() macro |
Any audio-thread code | Logger I/O in debug builds; blocks indefinitely |
MessageManager::getInstance() from audio thread |
Audio callbacks, DSP helpers | Not thread-safe; undefined behaviour |
apvts.getParameter(...) or apvts.state from audio thread |
processBlock and DSP helpers |
APVTS/ValueTree access is not an audio-thread data path; use raw pointer cache instead |
ValueTree listener callbacks assumed on audio thread |
Listener overrides | Dispatched via MessageManager; runs on message thread |
AudioBuffer::setSize() inside processBlock |
Buffer management code | Triggers allocation; causes xrun |
| Modifying MIDI buffer while iterating it | MIDI event loops | Iterator invalidation; undefined behaviour |
prepareToPlay not resetting all state (e.g. filters, envelopes, delay lines) |
prepareToPlay body |
Double-call leaves stale state; causes audio artefacts |
juce::CriticalSection::tryEnter() or enter() on audio thread |
processBlock, DSP helpers |
exit()/destructor does a syscall to wake waiting threads — not realtime-safe even with tryEnter() |
juce::SpinLock::enter() on audio thread |
processBlock, DSP helpers |
Busy-waits on audio thread — use tryEnter() + fallback only; non-audio thread should use progressive back-off |
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.
- 9d ago First seen · 83 lines · 115 tokens per session scan A 93fc3f875c76
juce-review is a skill published in the GitHub repository kunitoki/sonic-skills (19 stars, last pushed 3mo ago), licensed Unlicense. It adds 115 tokens to every session and 1,146 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-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-debt
Internal tech-debt transform pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Transforms the synthesized findings table into explicit debt items, each with a re-trigger condition; it does not rescan the diff. Findings only; never edits code.