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 CDCgov/cdc-open-viz --skill yarn-auditgit clone --depth 1 https://github.com/CDCgov/cdc-open-vizWrote 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/cdcgov/cdc-open-viz/yarn-audit)<a href="https://agentmods.dev/skills/cdcgov/cdc-open-viz/yarn-audit"><img src="https://agentmods.dev/badge/skills/cdcgov/cdc-open-viz/yarn-audit/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/cdcgov/cdc-open-viz/yarn-audit"><img src="https://agentmods.dev/badge/skills/cdcgov/cdc-open-viz/yarn-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 63 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00071 | $0.00893 |
| Opus 5.5 | $0.00028 | $0.00357 |
| Sonnet 5.5 | $0.00014 | $0.00179 |
| Haiku 4.5 | $0.00007 | $0.00089 |
Grade A, and why
yarn-audit 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 1mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yarn Audit
Resolve dependency audit findings with the smallest safe change.
Workflow
- Reproduce the dependency-only audit issue with
yarn audit --groups dependencies. - Identify the affected package names, severities, advisory paths, and whether the vulnerable package is direct or transitive.
- Check whether the problem is actually workspace version drift before changing versions:
- Run
yarn sync:check. - Search manifests with
rg -n '"<package-name>"' package.json packages/*/package.json.
- Run
- Choose the least invasive fix:
- If the same dependency or devDependency has inconsistent ranges across workspace manifests, use
syncpackfirst. - If a direct dependency is vulnerable, bump the direct dependency to the minimum safe range.
- If the vulnerable package is transitive and the parent can be bumped safely, upgrade the parent package instead of adding a broad override.
- If the vulnerable package is transitive and no safe parent bump is available, add or tighten a root
resolutionsentry for the minimum fixed version.
- If the same dependency or devDependency has inconsistent ranges across workspace manifests, use
- Regenerate the lockfile with
yarn installafter manifest changes. - Re-run
yarn audit --groups dependencies. - Report what changed, what advisory path was addressed, and any remaining findings.
Use Syncpack When Applicable
Treat syncpack as the first fix when audit work reveals monorepo drift rather than a true package-selection problem.
Use it when:
- Multiple workspaces declare the same package with different semver ranges and the audit fix needs them aligned.
- A package upgrade was applied in one workspace but other workspaces still pin an older vulnerable range.
- The repo already exposes
yarn sync:checkandyarn sync:fix, which this repository does.
Do not use it when:
- The issue is isolated to one package by design.
- The fix requires changing a root
resolutionsentry for a transitive dependency. - The audit finding is caused only by the lockfile selecting an old transitive version while manifest ranges are already aligned.
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.
- 1mo ago First seen · 98 lines · 71 tokens per session scan A cfa7577017d1
yarn-audit is a skill published in the GitHub repository CDCgov/cdc-open-viz (55 stars, last pushed today), licensed Apache-2.0. It adds 71 tokens to every session and 893 once invoked, about $0.0003 per session on Opus 5.5. 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
build-with-tinybase
Scaffold, extend, and verify reactive local-first JavaScript or TypeScript applications with TinyBase. Use when choosing TinyBase for in-memory tabular or key-value state, generating an app with create-tinybase, adding schemas or UI bindings, resolving TinyBase import paths, configuring browser or database…
chatgpt-app-submission
Inspect a ChatGPT Apps MCP server codebase and generate chatgpt-app-submission.json with app info suggestions, tool hint justifications, test cases, and negative test cases, then report review-check findings and outputSchema warnings for submission review.
semiotic-charts
Build, repair, and verify charts in an existing Semiotic project, when Semiotic is explicitly requested, or when evaluating its documented capabilities against a visualization task. Preserve the project's dependency and runtime constraints; routine changes in another charting stack and tasks without a chart do not…
infographic-item-creator
Generate or update infographic Item components for this repo (TypeScript/TSX in src/designs/items). Use when asked to design, implement, or modify data item visuals, layout logic, or registerItem composites.
data_analyst
Analyses datasets with professional rigour — statistical summaries, clear narratives, and well-chosen visualisations.
tableau-expert
Expert-level Tableau Desktop/Server, calculated fields, LOD expressions, dashboards, data blending, and performance optimization. Use when the user mentions BI, visualization, dashboards, LOD, or analytics, or when the task involves Calculated Fields, Level of Detail Expressions, Parameters and Dynamic Calculations…