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 agentmods add skills/imoonkey/openweb/nprnpx skills add imoonkey/openweb --skill nprgit clone --depth 1 https://github.com/imoonkey/openwebWhat 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 | $0.00000 | $0.00459 |
| Opus 5 | $0.00000 | $0.00230 |
| Sonnet 5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
npr 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.
What it actually says
NPR (National Public Radio)
Overview
Major U.S. public media news outlet. Public Algolia search index provides full article content including text, author, date, topics, and audio availability.
Workflows
Search for articles on a topic
searchArticles(query)→objectID,title,bodyTextgetArticle(objectID)→ fullbodyText,topics,bylines
Get today's top stories
getTopStories()→objectID,title,displayDategetArticle(objectID)→ fullbodyText,topics,image
Research a topic
searchArticles(query, hitsPerPage: 20)→objectID,title,topics- Filter by topic using
filters: "type:story AND topics:\"Health\""for section-specific results getArticle(objectID)→ fullbodyText,bylines
Operations
| Operation | Intent | Key Input | Key Output | Notes |
|---|---|---|---|---|
| searchArticles | find articles by keyword | query | objectID, title, bodyText, bylines, displayDate | entry point, paginated (page 0-indexed) |
| getArticle | full article content | objectID ← searchArticles/getTopStories | bodyText (full), title, bylines, topics, image | body is plain text |
| getTopStories | latest front page stories | — | objectID, title, bodyText, displayDate, topics | entry point, pre-filtered to homepage stories |
Quick Start
# Search for articles
openweb npr exec searchArticles '{"query": "artificial intelligence"}'
# Get a specific article (use objectID from search results)
openweb npr exec getArticle '{"objectID": "nx-s1-5777587"}'
# Get latest top stories
openweb npr exec getTopStories '{}'
# Search with pagination
openweb npr exec searchArticles '{"query": "economy", "hitsPerPage": 20, "page": 1}'
What ships with it
8 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 First seen · 44 lines · 0 tokens per session scan A 1c79ae20b38e
npr is a skill published in the GitHub repository imoonkey/openweb (56 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 459 tokens. 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
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.