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/blueskynpx skills add imoonkey/openweb --skill blueskygit 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 | $0.01543 |
| Opus 5 | $0.00000 | $0.00772 |
| Sonnet 5 | $0.00000 | $0.00309 |
| Haiku 4.5 | $0.00000 | $0.00154 |
Grade A, and why
bluesky 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bluesky
Overview
Bluesky AT Protocol social network — decentralized microblogging. Public read API at public.api.bsky.app, write ops via user's PDS (Personal Data Server).
Workflows
Browse a user's profile and posts
getProfile(actor)→ display name, bio, follower countsgetAuthorFeed(actor)→ user's posts →post.urigetPostThread(uri)→ full post with reply thread
Search and explore
searchActors(q)→ find users →actor.handlegetProfile(handle)→ full profile for a usersearchPosts(q)→ find posts (requires auth)
Feed consumption
getFeed(feed)→ discover/trending posts →post.urigetPostThread(uri)→ expand post with replies
Social graph
getFollowers(actor)→ who follows a usergetFollows(actor)→ who a user follows
Engage with a post
getAuthorFeed(actor)orgetFeed(feed)→ find post →uri,cidlikePost(uri, cid)→ like recordurirepost(uri, cid)→ repost recorduri- Reply:
getPostThread(uri)→ parenturi,cid; thread root →rootUri,rootCid createPost(text, replyTo={uri, cid, rootUri, rootCid})→ replyuri,cid
Undo engagement
getAuthorFeed(actor)orgetPostThread(uri)→ post withviewer.like,viewer.repostunlikePost(uri=viewer.like)→ removes likeunrepost(uri=viewer.repost)→ removes repostdeletePost(uri)→ deletes own post (uri← getAuthorFeed)
Manage follows, blocks, and mutes
getProfile(actor)→did,viewer.following,viewer.blocking,viewer.mutedfollow(subject=did)→ follow recorduriunfollow(uri=viewer.following)→ removes followblockUser(subject=did)→ block recorduriunblockUser(uri=viewer.blocking)→ removes blockmuteUser(actor)/unmuteUser(actor)→ toggle mute (uses handle or DID directly)
Notifications
getNotifications(limit)→ likes, reposts, follows, mentions, replies
Operations
| Operation | Intent | Key Input | Key Output | Notes |
|---|---|---|---|---|
| getProfile | user profile | actor (handle or DID) |
did, handle, displayName, bio, follower/following/post counts | entry point |
| getAuthorFeed | user's posts | actor ← getProfile |
feed[].post (uri, text, author, embeds, counts) | cursor pagination |
| getPostThread | post with replies | uri ← getAuthorFeed/getFeed |
thread.post (text, author, embeds, like/repost/reply/quote/bookmark counts), thread.replies[] | depth param controls reply depth |
| getFeed | custom feed | feed (AT URI of feed generator) |
feed[].post | cursor pagination, use known feed URIs |
| searchPosts | search posts | q |
posts[], hitsTotal | auth via bsky.app (localStorage_jwt) |
| searchActors | search users | q |
actors[] with profile info | cursor pagination |
| getFollowers | user's followers | actor ← getProfile |
followers[] profiles | cursor pagination |
| getFollows | user follows | actor ← getProfile |
follows[] profiles | cursor pagination |
| getPosts | batch fetch posts | uris[] ← getAuthorFeed/getFeed |
posts[] | max 25 URIs |
| createPost | publish post | text, replyTo ← getPostThread (uri, cid, rootUri, rootCid), langs |
uri, cid | auth required, write; replyTo optional |
| deletePost | delete post | uri ← createPost/getAuthorFeed |
success | auth required, write |
| likePost | like post | uri, cid ← getAuthorFeed/getFeed/getPostThread |
like record uri, cid | auth required, write |
| unlikePost | unlike post | uri ← post viewer.like |
success | auth required, write |
| repost | repost | uri, cid ← getAuthorFeed/getFeed/getPostThread |
repost record uri, cid | auth required, write |
| unrepost | undo repost | uri ← post viewer.repost |
success | auth required, write |
| follow | follow user | subject (DID) ← getProfile |
follow record uri, cid | auth required, write |
| unfollow | unfollow user | uri ← profile viewer.following |
success | auth required, write |
| blockUser | block user | subject (DID) ← getProfile |
block record uri, cid | auth required, write |
| unblockUser | unblock user | uri ← profile viewer.blocking |
success | auth required, write |
| muteUser | mute user | actor (handle or DID) |
success | auth required, write |
| unmuteUser | unmute user | actor (handle or DID) |
success | auth required, write |
| getNotifications | notifications | limit, cursor |
notifications[] (reason, author, record) | auth required, cursor pagination |
What ships with it
29 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/bluesky-pds.ts 11 KB runs code
- adapters/bluesky-public.ts 14 KB runs code
- DOC.md 7.3 KB
- examples/blockUser.example.json 223 B
- examples/createPost.example.json 225 B
- examples/deletePost.example.json 252 B
- examples/follow.example.json 220 B
- examples/getAuthorFeed.example.json 175 B
- examples/getFeed.example.json 231 B
- examples/getFollowers.example.json 174 B
- examples/getFollows.example.json 172 B
- examples/getNotifications.example.json 190 B
- examples/getPosts.example.json 221 B
- examples/getPostThread.example.json 235 B
- examples/getProfile.example.json 160 B
- examples/likePost.example.json 336 B
- examples/muteUser.example.json 196 B
- examples/repost.example.json 334 B
- examples/searchActors.example.json 169 B
- examples/searchPosts.example.json 198 B
- examples/unblockUser.example.json 255 B
- examples/unfollow.example.json 253 B
- examples/unlikePost.example.json 252 B
- examples/unmuteUser.example.json 198 B
- examples/unrepost.example.json 252 B
- manifest.json 694 B
- openapi.yaml 43 KB
- pipeline-gaps.md 3.7 KB
- PROGRESS.md 4.4 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 · 107 lines · 0 tokens per session scan A 11b4ba1271a0
bluesky is a skill published in the GitHub repository imoonkey/openweb (58 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,543 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.