Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/CDCgov/cdc-open-viznpx agentmods add skills/cdcgov/cdc-open-viz/readme-maintainerWrote 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/readme-maintainer)<a href="https://agentmods.dev/skills/cdcgov/cdc-open-viz/readme-maintainer"><img src="https://agentmods.dev/badge/skills/cdcgov/cdc-open-viz/readme-maintainer/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/readme-maintainer"><img src="https://agentmods.dev/badge/skills/cdcgov/cdc-open-viz/readme-maintainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to critical
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 →
- critical Prompt Injection · line 83 This content may contain harmful instructions that could cause physical harm if followed. CRITICAL: Review carefully before use.Fix: Remove all content that could lead to harmful outcomes. Add safety guardrails and human oversight for any high-risk operations.
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 | $0.00016 | $0.02329 |
| Opus 5 | $0.00008 | $0.01164 |
| Sonnet 5 | $0.00003 | $0.00466 |
| Haiku 4.5 | $0.00002 | $0.00233 |
Grade A, and why
README Maintainer 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain README.md with an accuracy-first pass.
Requirements:
- Inspect the current workspace before editing.
- Prefer minimal changes that correct drift between the README and checked-in files.
- Verify script names, paths, prerequisites, usage examples, and any documented generated or runtime directories.
- Replace unresolved placeholders (identified by brackets {}) in README metadata when the intended value can be inferred from the repository context; otherwise call out the uncertainty explicitly with a TODO.
- When filling
{Keywords}, use only exact terms from the approved taxonomy provided in the following JSON that has the terms grouped by top-level categories:
{ "Public Health Surveillance & Early Detection": [ "surveillance", "monitoring", "biosurveillance", "outbreak", "cluster", "disease tracking", "disease surveillance", "epidemiology", "epidemiologic", "syndromic", "case reporting", "case notification", "case-based", "vital statistics", "birth certificate", "death certificate", "mortality", "morbidity", "incidence", "prevalence", "nndss", "reportable", "notifiable", "sentinel", "signal detection" ], "Disease Prevention, Health Promotion & Community Programs": [ "prevention", "preventive", "risk reduction", "harm reduction", "screening", "early detection", "health promotion", "health improvement", "wellness", "behavior change", "behavioral", "intervention", "vaccination", "immunization", "vaccine", "immunisation", "health education", "outreach", "community", "community program", "communication", "health communication", "campaign", "social marketing", "guidelines", "recommendations", "best practices", "maternal health", "child health", "school health" ], "Clinical & Healthcare System Support": [ "clinical", "clinical support", "patient", "provider", "physician", "nursing", "nurse", "clinic", "hospital", "care team", "ehr", "electronic health record", "emr", "chart", "medical record", "treatment", "care management", "care coordination", "workflow", "order entry", "cpoe", "rounding", "telehealth", "telemedicine", "virtual care", "triage", "diagnosis", "clinical decision support", "cds", "clinical quality", "quality measure", "hitrust", "joint commission" ], "Data Exchange, Standards & Interoperability": [ "interoperability", "data exchange", "data sharing", "integration", "interface", "interfaces", "api", "rest api", "graphql", "hl7", "hl7v2", "v2", "fhir", "cda", "ccda", "health information exchange", "hie", "edi", "terminology", "vocabulary", "coding system", "codeset", "loinc", "snomed", "icd", "icd-10", "rxnorm", "xml", "json", "csv", "ndjson", "message mapping", "schema", "schema validation" ], "Analytics, Research & Public Health Decision Support": [ "analytics", "analysis", "data analysis", "data science", "reporting", "reports", "dashboard", "scorecard", "kpi", "business intelligence", "bi", "visualization", "chart", "graph", "statistics", "statistical", "model", "modeling", "forecasting", "projection", "scenario", "trend", "time series", "research", "study", "cohort", "evaluation", "outcome evaluation", "survey", "census", "questionnaire", "machine learning", "ml", "ai", "artificial intelligence", "natural language processing", "nlp", "risk stratification", "decision support", "policy analysis" ], "Laboratory Science, Genomics & Advanced Molecular Detection": [ "laboratory", "lab", "public health lab", "phl", "genomics", "genomic", "genotype", "sequencing", "sequence", "ngs", "next-generation sequencing", "molecular", "pcr", "assay", "serology", "viral load", "bioinformatics", "pipeline", "alignment", "variant calling", "lims", "laboratory information management", "specimen", "sample", "isolate", "strain", "amd", "advanced molecular detection", "phylogenetic" ], "Public Health Emergency Preparedness & Response": [ "emergency", "emergencies", "emergency response", "response", "preparedness", "readiness", "resilience", "all-hazards", "incident management", "incident command", "ics", "emergency operations", "eoc", "operations center", "rapid response", "surge", "deployment", "biopreparedness", "bioterrorism", "anthrax", "contingency plan", "emergency plan", "continuity of operations", "tabletop exercise", "drill", "exercise", "crisis", "disaster", "hurricane", "flood", "earthquake", "wildfire" ], "Administrative, Financial & Program Operations": [ "administrative", "administration", "operations", "operational", "program management", "project management", "pmo", "hr", "human resources", "personnel", "staffing", "training", "onboarding", "performance", "pmap", "budget", "finance", "financial", "cost", "costing", "billing", "claims", "revenue cycle", "procurement", "acquisition", "contract", "contracting", "grant", "grant management", "cooperative agreement", "co-ag", "governance", "compliance", "policy", "sop", "timekeeping", "travel", "inventory", "asset management" ] }
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 · 293 lines · 16 tokens per session scan A 080ce0219b65
README Maintainer is a skill published in the GitHub repository CDCgov/cdc-open-viz (55 stars, last pushed 4d ago), licensed Apache-2.0. It adds 16 tokens to every session and 2,329 once invoked, about $0.0001 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
hot-paths
AG Charts runtime hot paths: which files run per datum, per frame or per interaction, the invariants each tier must hold, and how to evidence a performance claim. Use when reviewing a change that touches series, scene, data-model, scale, interaction or DOM code, when asked whether a diff will cost performance, or when…
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, configuring browser or database persistence, configuring MergeableStore…
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…
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
ss-lint
Quick automated lint — detects common design system violations in seconds.