bluesky

A connection to Bluesky, a decentralized social network for short posts. It can read profiles, posts, feeds, replies, followers, and follows, and can perform actions such as liking, reposting, posting, and replying.

In plain words
What is it for?
Use it to find users or posts, read reply threads, inspect social connections, follow feeds, like or repost content, and publish posts or replies.
Why use it?
It lets an agent explore Bluesky conversations and manage supported social actions through its public service and the user’s account server.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/imoonkey/openweb/bluesky
Any agent
npx skills add imoonkey/openweb --skill bluesky
Clone the repo
git clone --depth 1 https://github.com/imoonkey/openweb

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,543 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 11b4ba1271a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 2 executable files (adapters/bluesky-pds.ts, adapters/bluesky-public.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src/sites/bluesky/SKILL.md · 107 lines

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

  1. getProfile(actor) → display name, bio, follower counts
  2. getAuthorFeed(actor) → user's posts → post.uri
  3. getPostThread(uri) → full post with reply thread

Search and explore

  1. searchActors(q) → find users → actor.handle
  2. getProfile(handle) → full profile for a user
  3. searchPosts(q) → find posts (requires auth)

Feed consumption

  1. getFeed(feed) → discover/trending posts → post.uri
  2. getPostThread(uri) → expand post with replies

Social graph

  1. getFollowers(actor) → who follows a user
  2. getFollows(actor) → who a user follows

Engage with a post

  1. getAuthorFeed(actor) or getFeed(feed) → find post → uri, cid
  2. likePost(uri, cid) → like record uri
  3. repost(uri, cid) → repost record uri
  4. Reply: getPostThread(uri) → parent uri, cid; thread root → rootUri, rootCid
  5. createPost(text, replyTo={uri, cid, rootUri, rootCid}) → reply uri, cid

Undo engagement

  1. getAuthorFeed(actor) or getPostThread(uri) → post with viewer.like, viewer.repost
  2. unlikePost(uri=viewer.like) → removes like
  3. unrepost(uri=viewer.repost) → removes repost
  4. deletePost(uri) → deletes own post (uri ← getAuthorFeed)

Manage follows, blocks, and mutes

  1. getProfile(actor)did, viewer.following, viewer.blocking, viewer.muted
  2. follow(subject=did) → follow record uri
  3. unfollow(uri=viewer.following) → removes follow
  4. blockUser(subject=did) → block record uri
  5. unblockUser(uri=viewer.blocking) → removes block
  6. muteUser(actor) / unmuteUser(actor) → toggle mute (uses handle or DID directly)

Notifications

  1. 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

Read the full file on GitHub · 107 lines

Changes

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.

  1. 2d ago First seen · 107 lines · 0 tokens per session scan A 11b4ba1271a0

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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.

microsoft/vscode · 56 tokens

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.

microsoft/vscode · 62 tokens