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 skills add tang-vu/social-posting-skills --skill post-blueskygit clone --depth 1 https://github.com/tang-vu/social-posting-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tang-vu/social-posting-skills/post-bluesky)<a href="https://agentmods.dev/skills/tang-vu/social-posting-skills/post-bluesky"><img src="https://agentmods.dev/badge/skills/tang-vu/social-posting-skills/post-bluesky/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tang-vu/social-posting-skills/post-bluesky"><img src="https://agentmods.dev/badge/skills/tang-vu/social-posting-skills/post-bluesky.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00015 | $0.01564 |
| Opus 5 | $0.00008 | $0.00782 |
| Sonnet 5 | $0.00003 | $0.00313 |
| Haiku 4.5 | $0.00002 | $0.00156 |
Grade A, and why
post-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 12d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bluesky Posting Skill
Platform Overview
Bluesky (bsky.app) is a decentralized social platform built on the AT Protocol. It's growing rapidly among tech communities and is an excellent platform for reaching developers, designers, journalists, and early adopters. Think of it as what Twitter was in 2009-2012 — conversational, authentic, and community-driven. 20M+ users and growing.
Platform Constraints
- Character Limit: 300 characters per post
- Media: Up to 4 images per post
- Links: Displayed as rich cards (use for blog posts, projects)
- Hashtags: NOT supported — do not use them
- Threads: Supported via reply chains
- Custom Feeds: Users can create and subscribe to algorithmic feeds
- Decentralized: Your account is portable across servers via AT Protocol
Link Placement Strategy
RECOMMENDED: Put links in a REPLY to your own post.
- Bluesky's 300-char limit makes every character precious -- links eat into this
- Links generate rich card previews which can dominate the post visually
- Best strategy: Post a conversational text-only post, then reply with the link
- Exception: If the link IS the content (sharing an article), a link post is fine
- The community values authentic conversation over link-sharing
Posting Steps (Browser Automation)
- Navigate to
https://bsky.app/ - Wait for page load (must be logged in)
- Click the compose button (pencil/plus icon)
- Wait for compose modal to open
- Type content in the text area (ASCII English only, max 300 chars)
- Click "Post" button
- Verify post appears on your profile timeline
Thread Posting (Reply Chain)
Bluesky does NOT have a native "Add to thread" feature in the composer. Build threads by replying to yourself.
- Post the first post normally
- Navigate to YOUR OWN post (or find it on your profile)
- Click the Reply button on your post
- Type the next post in the reply composer
- Click "Post"
- Repeat for each additional post in the thread
Thread Strategy Tips:
- Number your posts: "1/", "2/", etc.
- First post = hook (must be compelling since there's no auto-unfold)
- Each reply should work as standalone AND connect to the chain
- Keep threads shorter (3-5 posts) since there's no "Post all" feature
- Link to full content in the last reply
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.
- 12d ago First seen · 166 lines · 15 tokens per session scan A 117539b7ffa8
post-bluesky is a skill published in the GitHub repository tang-vu/social-posting-skills (9 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 1,564 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
auto-research
Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.
agent-orchestrator
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
e2e-automator
Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.
accessibility-tester
Professional Accessibility Tester Expert skill. Implement robust test suites and automated quality checks for modern web/mobile applications.