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 clap-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/clap-review)<a href="https://agentmods.dev/skills/kunitoki/sonic-skills/clap-review"><img src="https://agentmods.dev/badge/skills/kunitoki/sonic-skills/clap-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/clap-review"><img src="https://agentmods.dev/badge/skills/kunitoki/sonic-skills/clap-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 | $0.00105 | $0.01106 |
| Opus 5 | $0.00053 | $0.00553 |
| Sonnet 5 | $0.00021 | $0.00221 |
| Haiku 4.5 | $0.00011 | $0.00111 |
Grade A, and why
clap-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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAP Plugin Review
CLAP's threading model is explicit by design — every host method and extension entry point is tagged with a thread requirement. Violations are silent at compile time and often only surface under specific host implementations.
Step 0 — Run universal checks first
Invoke audio-dsp-review and audio-numerics-review before this skill. This skill adds CLAP-specific spec compliance checks on top; it does not replace realtime-safety or numerics reviews.
Step 1 — Identify plugin structure
Locate and characterize the plugin's registered interfaces:
| Item | What to check |
|---|---|
clap_plugin_t |
process, activate, deactivate, start_processing, stop_processing implemented |
Extensions returned by get_extension |
Which of: audio-ports, params, state, gui, note-ports, log, timer-support, posix-fd-support |
Host extensions queried in init |
Which host callbacks are cached; which thread they may be called from |
clap_plugin_descriptor_t |
id is stable and reverse-DNS formatted; features declared correctly |
Step 2 — Scan for CLAP-specific violations
| Violation | Where | Risk |
|---|---|---|
Holding clap_event_* pointer after callback returns |
process() |
Use-after-free — events are host-owned, lifetime ends when process() returns |
| Calling a host method from the wrong thread context | audio↔main boundary | Spec violation — obey each method's [main-thread], [audio-thread], or [thread-safe] tag |
| State save/restore doing I/O on wrong thread | save/load in state extension |
Thread safety violation — state methods run on main thread, not audio thread |
Extension methods not guarded by thread_check |
any extension handler | Data race — extensions have per-method thread requirements; check each one |
process() returning wrong clap_process_status |
process() |
Host misinterprets plugin state — CLAP_PROCESS_SLEEP vs CLAP_PROCESS_CONTINUE affects scheduling |
| Param IDs not stable across save/load cycles | params extension | Broken parameter recall — param IDs must be stable for the lifetime of the plugin ID |
| Audio port channel counts mismatched at runtime vs declared | audio-ports extension | Buffer overread/underwrite — host allocates buffers based on declared port config |
Calling host params->request_flush() from process() |
params extension | Spec violation — request_flush is [thread-safe, !audio-thread]; emit output events during process() instead |
Querying plugin extensions before plugin->init() |
host/plugin setup | Spec violation — get_extension() is forbidden before init, but allowed during and after init |
Not handling CLAP_EVENT_TRANSPORT when transport-aware |
process() |
Incorrect playback position — transport events must be consumed each process call |
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 · 82 lines · 105 tokens per session scan A da34dcf0f5a5
clap-review is a skill published in the GitHub repository kunitoki/sonic-skills (19 stars, last pushed 3mo ago), licensed Unlicense. It adds 105 tokens to every session and 1,106 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".
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.