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/hackernewsnpx skills add imoonkey/openweb --skill hackernewsgit 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 | $0.01623 |
| Opus 5 | $0.00000 | $0.00812 |
| Sonnet 5 | $0.00000 | $0.00325 |
| Haiku 4.5 | $0.00000 | $0.00162 |
Grade A, and why
hackernews scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hacker News
Overview
Tech news aggregator by Y Combinator. Reads via Algolia Search API and Firebase API (node-direct). Writes via browser page context.
Workflows
Browse and read a story
getTopStories→ pick story → noteobjectIDgetStoryDetail(id)→ title, url, points, author, nested comment tree
Upvote a story
getTopStories→ pick story →objectIDupvoteStory(id=objectID)→{ok, id}(requires login)unvoteStory(id=${prev.upvoteStory.id})→{ok, id}— reverses the upvote (only valid while upvoted)
Comment on a story
getStoryDetail(id)→item.idaddComment(parent=item.id, text)→{ok, parent, id}—idis the new comment's id (requires login)deleteComment(id=${prev.addComment.id})→{ok, id}— must be within HN's ~2-hour delete window
Reply to a comment
getStoryDetail(id)→children[]→ pick comment →comment.idaddComment(parent=comment.id, text)→{ok, parent, id}— posts reply (requires login)
Explore a user
getUserProfile(id)→ karma, created, aboutgetUserSubmissions(id)→ stories they postedgetUserComments(id)→ their comment history
Find stories from a domain
getStoriesByDomain(query)→ all stories linking to that domain
Read latest activity
getNewComments→ newest comments across all stories
Operations
| Operation | Intent | Key Input | Key Output | Transport |
|---|---|---|---|---|
| getTopStories | browse top stories | — | objectID, title, url, author, points, num_comments | L1 node (Algolia) |
| getNewestStories | browse newest | — | same as above | L1 node (Algolia) |
| getBestStories | all-time highest-voted | — | same as above | L1 node (Algolia) |
| getAskStories | recent Ask HN | — | same as above | L1 node (Algolia) |
| getShowStories | recent Show HN | — | same as above | L1 node (Algolia) |
| getJobPostings | browse jobs | — | objectID, title, url, created_at | L1 node (Algolia) |
| getFrontPageStories | time-based front page | — | same as feeds | L1 node (Algolia) |
| getStoryDetail | story + comment tree | id (item ID) | id, title, url, points, children[] | L1 node (Algolia) |
| getUserProfile | user profile | id (username) | id, karma, created, about | L1 node (Firebase) |
| getNewComments | newest comments | — | objectID, author, comment_text, story_title | L1 node (Algolia) |
| getStoryComments | comment thread | id, limit? | storyId, commentCount, comments[] | adapter (Algolia) |
| getStoriesByDomain | recent domain stories | query (domain) | objectID, title, url, author, points | L1 node (Algolia) |
| getUserSubmissions | user's stories | id (username) | objectID, title, url, author, points | adapter (Algolia) |
| getUserComments | user's comments | id (username) | objectID, author, comment_text | adapter (Algolia) |
| upvoteStory | upvote item | id <- feeds/getStoryDetail | ok, id | adapter (page) |
| unvoteStory | reverse upvote | id <- upvoteStory | ok, id | adapter (page) |
| addComment | post comment | parent <- getStoryDetail, text | ok, parent, id | adapter (page) |
| deleteComment | delete own comment | id <- addComment | ok, id | adapter (page); ~2-hour window |
What ships with it
23 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/hackernews.ts 5.6 KB runs code
- DOC.md 7.5 KB
- examples/add_comment.example.json 552 B
- examples/delete_comment.example.json 295 B
- examples/get_ask_stories.example.json 178 B
- examples/get_best_stories.example.json 179 B
- examples/get_front_page_stories.example.json 184 B
- examples/get_job_postings.example.json 179 B
- examples/get_new_comments.example.json 179 B
- examples/get_newest_stories.example.json 181 B
- examples/get_show_stories.example.json 179 B
- examples/get_stories_by_domain.example.json 220 B
- examples/get_story_comments.example.json 231 B
- examples/get_story_detail.example.json 202 B
- examples/get_top_stories.example.json 178 B
- examples/get_user_comments.example.json 206 B
- examples/get_user_profile.example.json 205 B
- examples/get_user_submissions.example.json 209 B
- examples/unvote_story.example.json 294 B
- examples/upvote_story.example.json 278 B
- manifest.json 427 B
- openapi.yaml 31 KB
- PROGRESS.md 9.2 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 · 138 lines · 0 tokens per session scan A cf6028c736f6
hackernews 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 1,623 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…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
mintlify-preview
Run the public Mintlify product docs site locally for live preview. Use when previewing or iterating on docs under docs/ (.mdx/.md pages, docs.json nav), or when the user says "start the docs", "run mintlify", "preview the docs site".