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/mediumnpx skills add imoonkey/openweb --skill mediumgit 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 | $0.00892 |
| Opus 5 | $0.00000 | $0.00446 |
| Sonnet 5 | $0.00000 | $0.00178 |
| Haiku 4.5 | $0.00000 | $0.00089 |
Grade A, and why
medium 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Medium
Overview
Blogging and publishing platform. Content platform archetype. Search articles, browse topic feeds, discover curated lists, explore writers, clap articles, follow writers, and save bookmarks via Medium's GraphQL API.
Workflows
Browse articles by topic
getRecommendedTags→ pick tag →tagSluggetTagFeed(tagSlug)→ posts withpostIdgetArticle(postId)→ full article detail
Search and read
searchArticles(query)→ results with titles, URLs- Pick article URL → extract
postIdfrom URL getArticle(postId)→ full detail
Explore writers for a topic
getTagWriters(tagSlug)→ writers/publications withuserId, bio, follower count
Discover curated content
getTagCuratedLists(tagSlug)→ staff-picked reading lists- Lists contain posts with
postId→getArticle(postId)
Engage with content (requires login)
getTagFeed(tagSlug)→posts[].postIdclapArticle(postId ← posts[].postId, numClaps?)→clapCount,viewerClapCount(numClaps 1–50, default 1)saveArticle(postId ← posts[].postId)→catalogItemIdunsaveArticle(postId ← posts[].postId)→ adapter resolvespostId → catalogItemIdviagetPredefinedCatalog().itemsConnection, then issues delete
Follow a writer (requires login)
getTagWriters(tagSlug)→ writers withuserIdfollowWriter(userId ← getTagWriters)→isFollowingunfollowWriter(userId)→ removes follow
Operations
| Operation | Intent | Key Input | Key Output | Notes |
|---|---|---|---|---|
| searchArticles | search articles by keyword | query | title, subtitle, url | DOM extraction; entry point |
| getArticle | get full article detail | postId ← getTagFeed/searchArticles | title, author, claps, readingTime, isLocked | GraphQL PostDetailQuery |
| getTagFeed | latest articles for a tag | tagSlug | posts[], pageInfo | GraphQL; paginated |
| getTagCuratedLists | curated reading lists for a tag | tagSlug | lists[] with post items | GraphQL |
| getTagWriters | recommended writers for a tag | tagSlug, first?, after? | publishers[], pageInfo | GraphQL; paginated |
| getRecommendedFeed | trending/top articles | limit? | posts[] with feedId, reason | GraphQL; personalized when logged in |
| getRecommendedTags | trending topic tags | — | tags[] with slug | entry point |
| getPostClaps | clap count for a post | postId ← getTagFeed | postId, clapCount | GraphQL |
| getRecommendedWriters | writers to follow | — | publishers[] | GraphQL |
| clapArticle | clap (upvote) a post | postId | clapCount, viewerClapCount | SAFE write; requires auth |
| followWriter | follow a writer | userId ← getTagWriters | isFollowing | SAFE write; requires auth |
| saveArticle | save to reading list | postId | saved, catalogItemId | SAFE write; requires auth |
| unfollowWriter | unfollow a writer | userId ← getTagWriters | isFollowing | CAUTION write; requires auth |
| unsaveArticle | remove from reading list | postId | removed | CAUTION write; requires auth |
What ships with it
21 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.
- adapters/medium-graphql.ts 18 KB runs code
- adapters/queries.ts 7.2 KB runs code
- DOC.md 6.2 KB
- examples/clapArticle.example.json 217 B
- examples/followWriter.example.json 203 B
- examples/getArticle.example.json 201 B
- examples/getPostClaps.example.json 203 B
- examples/getRecommendedFeed.example.json 195 B
- examples/getRecommendedTags.example.json 183 B
- examples/getRecommendedWriters.example.json 186 B
- examples/getTagCuratedLists.example.json 208 B
- examples/getTagFeed.example.json 201 B
- examples/getTagWriters.example.json 217 B
- examples/saveArticle.example.json 202 B
- examples/searchArticles.example.json 215 B
- examples/unfollowWriter.example.json 263 B
- examples/unsaveArticle.example.json 262 B
- manifest.json 444 B
- openapi.yaml 24 KB
- pipeline-gaps.md 2.1 KB
- PROGRESS.md 4.7 KB
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 · 73 lines · 0 tokens per session scan A 5dd34f647af5
medium 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 892 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…