Borrowing it
Nothing to install: this file belongs to kamiazya/whiteboard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kamiazya/whiteboard/main/.claude/skills/audit-triage/SKILL.mdgit clone --depth 1 https://github.com/kamiazya/whiteboardWrote 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/kamiazya/whiteboard/audit-triage)<a href="https://agentmods.dev/skills/kamiazya/whiteboard/audit-triage"><img src="https://agentmods.dev/badge/skills/kamiazya/whiteboard/audit-triage/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/kamiazya/whiteboard/audit-triage"><img src="https://agentmods.dev/badge/skills/kamiazya/whiteboard/audit-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 49 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.01909 |
| Opus 5 | $0.00049 | $0.00955 |
| Sonnet 5 | $0.00020 | $0.00382 |
| Haiku 4.5 | $0.00010 | $0.00191 |
Grade A, and why
audit-triage 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 2d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit-Triage (whiteboard)
The per-diff review workflow only sees a change. Standing problems — a feature that builds but isn't wired (the Cloudflare-shell class), a god module, a contract defined twice, a critical path with no test, onboarding that breaks on a clean clone — never show up in a diff. audit-triage is the recurring sweep that finds them and turns them into tickets.
Run it
Workflow({ scriptPath: '.claude/workflows/audit-triage.workflow.mjs',
args: { scope?, dimensions?, cwd?, auditorAgent?, verifyFloor? } })
- scope: free-text area to focus (e.g.
"apps/web and its migration") or omit for the whole repo. Narrow the scope for a faster, deeper pass on a hot area. - dimensions: defaults to the six below. Pass a subset to focus, or supply
{name, content}objects to inject externalized criteria (see below). Legacy plain-string dimensions are still supported. - auditorAgent: defaults to
Explore(read-only, always registered). The tunedcodebase-auditoragent is NOT registered until a session reload (see theworkflow-authoringskill's mid-session-agent-registration gotcha) — passauditorAgent: 'codebase-auditor'only after a reload. - verifyFloor: lowest severity that gets an adversarial verify pass (default
HIGH). Verification kills false positives — the audit favors recall, verify restores precision.
It returns triaged.items[] (read-only), plus coverage-honesty fields: dimensionsAudited (dimensions that actually produced a result), failedDimensions (a dimension's auditor agent returned nothing — a LOW coverage-gap advisory finding is also injected into triaged so a silent gap can't hide), and notApplicable (an auditor explicitly opted out via notApplicable:true because the dimension doesn't apply to this scope). Check failedDimensions before trusting a clean run. The workflow cannot create Tasks — the integrator (main session) files the survivors.
The six dimensions
wiring-gaps (looks-done-isn't) · architecture (seams/coupling) · maintainability (size/dup/dead-code) · contract-drift (hand-written-vs-Zod, casts) · test-gaps (untested critical paths, skips) · dev-experience (clean-clone friction).
What ships with it
7 files 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.
- 2d ago Changed 1cfc625108ca
- 7d ago Changed · +13 lines 49a354e91d6f
- 12d ago First seen · 93 lines · 99 tokens per session scan A 7c5bea25fda5
audit-triage is a skill published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 99 tokens to every session and 1,909 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…