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 yup-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/yup-review)<a href="https://agentmods.dev/skills/kunitoki/sonic-skills/yup-review"><img src="https://agentmods.dev/badge/skills/kunitoki/sonic-skills/yup-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/yup-review"><img src="https://agentmods.dev/badge/skills/kunitoki/sonic-skills/yup-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 | $0.00117 | $0.01461 |
| Opus 5 | $0.00059 | $0.00731 |
| Sonnet 5 | $0.00023 | $0.00292 |
| Haiku 4.5 | $0.00012 | $0.00146 |
Grade A, and why
yup-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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YUP Audio Plugin Review
YUP looks JUCE-like in places, but its plugin API has its own parameter handles, bus layout, editor contract, and wrapper behavior. Review those directly instead of applying APVTS rules.
Step 0 - Run universal checks first
Invoke audio-dsp-review and audio-numerics-review before this skill. This skill adds YUP-specific checks on top; it does not replace realtime-safety or numerics reviews.
Step 1 - Identify plugin structure
Locate the core classes and boundaries:
yup::AudioProcessor- audio thread ownsprocessBlock; wrapper/host code calls lifecycle, state, and preset methodsyup::AudioProcessorEditor- UI/message thread only; never call from audio threadyup::AudioParameter- atomic scalar value plus listeners for host/UI notificationyup::AudioParameterHandle- audio-thread smoothing/read path; initialise inprepareToPlayyup::AudioBusLayout- immutable I/O contract exposed to plugin wrappersextern "C" yup::AudioProcessor* createPluginProcessor()- plugin entry point used by wrappers
Step 2 - Scan for YUP violations
| Violation | Where to look | Risk |
|---|---|---|
AudioParameterHandle default-constructed and used before prepareToPlay |
Members and processBlock |
Null parameter assertion/crash; wrong smoothing state |
Missing handle.updateNextAudioBlock() |
processBlock |
Automation and smoothing lag or never update |
Recreating AudioParameterHandle in processBlock |
Audio callback | Reinitialises smoothing and may add avoidable work/glitches |
setValueNotifyingHost(), beginChangeGesture(), or endChangeGesture() from audio code |
processBlock, MIDI handlers, DSP helpers |
Listener/host notification path is not a realtime data path |
Allocating voices, buffers, MemoryBlock, String, std::vector, or smart-pointer objects in processBlock |
MIDI note-on, scratch buffers, metering | Heap traffic causes xruns |
YUP_DBG, Logger::writeToLog, File, URL, JSON/XML, or string formatting in audio code |
Debug and error paths | Logging/I/O/allocation on audio thread |
| Hard-coded channel pointers without layout checks | getWritePointer(0/1) and bus setup |
Mono, sidechain, or unusual host layout crashes/corrupts audio |
Mutating MidiBuffer while iterating it |
MIDI loops | Iterator invalidation or unbounded allocation |
prepareToPlay not resetting all DSP and note state |
Lifecycle methods | Host reactivation leaves stale filter history, held notes, or ramps |
flush() missing for synths/effects with tails or voices |
CLAP reset handling | Host reset leaves hanging notes or stale delay/reverb tails |
| State load/save left unimplemented | loadStateFromMemory, saveStateIntoMemory |
DAW session recall and presets fail |
Long work under getProcessLock() or state swaps with no handoff |
UI/state/background code | Processing may skip under CLAP try-lock or race under other wrappers |
| Editor stores raw processor-owned UI pointers or processor stores editor pointer | Editor/processor members | Dangling pointer when host closes editor |
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 · 97 lines · 117 tokens per session scan A e7341d1c83de
yup-review is a skill published in the GitHub repository kunitoki/sonic-skills (19 stars, last pushed 3mo ago), licensed Unlicense. It adds 117 tokens to every session and 1,461 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.