Crier Cross-Posting Workflow

Crier cross-posts blog content to multiple platforms. The blog is the canonical source of truth.

Division of labor:

• Crier does mechanics: API calls, registry tracking, clipboard, browser
• Claude does judgment: summaries, error handling, user interaction

Platform Reference

Platform	Mode	Limit	Updates?	Notes
devto	API	∞	Yes	Tags auto-sanitized (no hyphens)
hashnode	API	∞	Yes
bluesky	API	300	No	Short-form, needs rewrite
mastodon	API	500	Yes	Short-form, needs rewrite
medium	import	∞	No	User imports from canonical URL
twitter	paste	280	No	Short-form, copy-paste
threads	paste	500	No	Short-form, copy-paste
linkedin	paste	∞	No	Copy-paste

Modes:

• API = automatic posting via API
• import = user imports from canonical URL (like Medium)
• paste = user copy-pastes (content goes to clipboard)

Configuration

Crier uses a single global config file. No local config, no --project flag.

Global Config (~/.config/crier/config.yaml)

# Where the content project lives (for registry + resolving relative content_paths)
site_root: ~/github/repos/metafunctor

# Content discovery
content_paths:
  - content/post
site_base_url: https://metafunctor.com
exclude_patterns:
  - _index.md
file_extensions:
  - .md

# Defaults
default_profile: everything
rewrite_author: claude-code

# API keys
platforms:
  bluesky:
    api_key: handle:app-password
  devto:
    api_key: ...

# Publishing profiles
profiles:
  blogs:
    - devto
    - hashnode
    - medium
  social:
    - bluesky
    - mastodon
  everything:
    - blogs
    - social

Key points:

• site_root tells crier where the content project and registry live
• Registry is at <site_root>/.crier/registry.yaml
• Content paths resolve relative to site_root
• Works from any directory — no need to cd to the project
• Precedence: global config < env vars < CLI args
• Override config path: CRIER_CONFIG env var
• Override API keys: CRIER_{PLATFORM}_API_KEY env vars

Checking Publication Status

Before cross-posting, check what's already published:

# Single file status
crier status content/post/2026-02-13-slug/index.md

# What needs publishing
crier audit                     # All content
crier audit content/post        # Just posts
crier audit --since 1w          # Last week

# Site-wide registry overview (no API calls)
crier summary
crier summary --json

# Check API keys are working
crier doctor

Typical Workflow (Cross-Posting from Any Repo)

The common pattern: you're working in a project repo (not the blog repo), write a blog post about it, then cross-post. Crier works globally via site_root, so no need to switch directories.

1. Write/update blog post in metafunctor repo
2. Run audit to see what needs posting
3. Publish to long-form platforms (devto, hashnode) from the canonical file
4. Write short-form rewrites and publish (bluesky, mastodon) using --rewrite
5. Verify audit is clean

Step-by-step

CRITICAL: Always publish from the canonical content file. Never create temp files for different platforms. The registry tracks publications by source file path. Publishing from temp files breaks audit tracking.

# 1. Check what needs posting
crier audit content/post/2026-02-13-my-article/index.md

# 2. Publish to long-form (uses the actual content file)
crier publish content/post/2026-02-13-my-article/index.md --to devto
crier publish content/post/2026-02-13-my-article/index.md --to hashnode

# 3. For short-form, Claude writes rewrites and publishes via --rewrite
#    ALWAYS use --rewrite on the CANONICAL file — never publish temp files
crier publish content/post/2026-02-13-my-article/index.md --to bluesky \
  --rewrite "Hook text about the interesting insight" --rewrite-author "claude-code"
crier publish content/post/2026-02-13-my-article/index.md --to mastodon \
  --rewrite "Slightly longer summary with #hashtags" --rewrite-author "claude-code"

# 4. Verify audit is clean
crier audit content/post/2026-02-13-my-article/index.md

Never use temp files. The --rewrite flag exists precisely so you can publish platform-specific content while keeping the registry pointed at the canonical source file. If you write to /tmp/claude/crier-bluesky.md and publish that, the registry records the temp path and audit breaks.

Complete Dialogue Examples

Example 1: Cross-post a new article

User: cross-post my new blog post to the usual platforms

Claude: I'll cross-post content/post/2026-01-04-my-article/index.md

Let me check what's needed:
[runs: crier audit content/post/2026-01-04-my-article/index.md]

Platforms to post:
- devto (API) - will auto-post
- hashnode (API) - will auto-post
- bluesky (API, 300 chars) - I'll write a summary
- mastodon (API, 500 chars) - I'll write a summary
- medium (import) - you'll import from your URL

Proceed?

User: yes

Claude: [runs API posts for devto, hashnode]
[generates summaries and posts to bluesky, mastodon with --rewrite]

Done:
- devto: https://dev.to/user/my-article-abc
- hashnode: https://user.hashnode.dev/my-article
- bluesky: posted announcement
- mastodon: posted announcement

For Medium, import from your canonical URL:
https://yourblog.com/post/2026-01-04-my-article/

Go to: https://medium.com/p/import

[runs: crier publish article.md --to medium --yes]

Did you import to Medium successfully?

User: yes

Claude: All platforms complete.

Example 2: Handling short-form platforms

User: post this to bluesky

Claude: [runs: crier publish article.md --to bluesky]

Error: Content too long for bluesky: 5000 characters (limit: 300)

I'll write a short announcement:

"New post: Exploring the mathematics of uncertainty - how
probabilistic thinking can transform how we approach
complex problems."

(198 chars + URL = within limit)

[runs: crier publish article.md --to bluesky \
  --rewrite "New post: Exploring..." --rewrite-author "claude-code"]

bluesky: https://bsky.app/profile/user/post/abc123

Example 3: Import mode (Medium)

User: post to medium

Claude: Medium uses URL import. I'll set this up:

[runs: crier publish article.md --to medium --yes]

Import your article from this URL:
https://yourblog.com/post/2026-01-04-my-article/

Go to: https://medium.com/p/import

Did the import work?

User: yes

Claude: Registered in crier. Done!

Example 4: Manual paste mode (Twitter)

User: share on twitter

Claude: Twitter uses copy-paste mode.

[runs: crier publish article.md --to twitter --yes]

I've copied this to your clipboard:
"New post: My Article Title - exploring key concepts...

https://yourblog.com/post/my-article/"

Go to: https://twitter.com/compose/tweet

Did you post it?

User: yes

Claude: Registered. All done!

Workflow Decision Tree

User wants to cross-post

1. Audit first: crier audit <file> or crier audit for all content
2. Show platforms: List what will happen for each platform
3. Get confirmation: Simple "Proceed?" - trust the user
4. Execute by type:
   • API long-form: crier publish <file> --to <platform>
   • API short-form: Generate summary, use --rewrite
   • Import mode: crier publish ... --to medium --yes, tell user to import
   • Paste mode: crier publish ... --to twitter --yes, tell user to paste
5. Report results: Show all successes, ask about manual platforms

User says something changed

1. Run crier audit to see dirty markers
2. For platforms that support update: re-run publish (auto-updates)
3. For platforms without update (bluesky, twitter): tell user they must delete/repost manually

Failure handling

• Continue through all platforms even if some fail
• Report all failures at the end
• Don't ask user to retry - just report what happened

Writing Rewrites

You ARE the rewriter. Don't use --auto-rewrite in interactive Claude Code sessions.

Rewrite Guidelines by Platform

Platform	Limit	Voice	Format
Bluesky	300	Conversational, personal	Hook + key insight. No hashtags.
Mastodon	500	Slightly more detailed	Can include 2-3 hashtags at end.
Twitter	280	Punchy, provocative	Can thread for longer content.
Threads	500	Casual, exploratory	Like talking to a friend.
LinkedIn	∞	Professional, structured	3-4 paragraphs, accomplishment-framed.

Rewrite Process

1. Read the full post (or at least title + description + first few paragraphs)
2. Identify the single most interesting or surprising insight
3. Write the rewrite around that insight — not a generic summary
4. Show the user before posting — they may want to adjust tone
5. Pass to crier via --rewrite

Anti-Patterns

• "New blog post: [title]" — boring, no hook
• "I wrote about X" — self-referential
• "Check out my latest..." — generic call-to-action
• Summarizing the entire post — pick ONE angle
• Including the URL in your rewrite — crier appends it automatically

Good Rewrites Lead with the Insight

• "TIL Bloom filters can give false positives but never false negatives — and the math behind why is beautiful."
• "What if the problem isn't the algorithm but the loss function?"
• "After 4 years of building 120+ open-source projects, I finally mapped how they all connect."

When to Use --auto-rewrite Instead

Situation	Use
Interactive Claude session	Claude writes rewrite, passes via --rewrite
Batch/bulk posting (10+ items)	--auto-rewrite for throughput
User says "just post it"	--auto-rewrite as shortcut
User cares about quality	Claude writes it, shows for approval

Interpreting Audit Scope

The crier audit command scans all directories in content_paths by default. Users often want to scope to specific content types.

Reading user intent:

User says...	Likely scope
"last month of content", "recent content", "what needs posting"	All content (crier audit --since 1m)
"blog posts", "posts", "articles"	crier audit content/post
"projects"	crier audit content/projects
"papers", "research"	crier audit content/papers

When uncertain:

• Run crier config show to see configured content paths
• Make a reasonable choice based on available clues
• If wrong, the user will clarify

Key Commands

# Check what needs publishing
crier audit
crier audit content/post/my-article/index.md

# Publish to API platform
crier publish article.md --to devto

# Publish with rewrite for short-form
crier publish article.md --to bluesky \
  --rewrite "Short announcement text" \
  --rewrite-author "claude-code"

# Import/paste mode (skips interactive prompts)
crier publish article.md --to medium --yes
crier publish article.md --to twitter --yes

# Registry summary (no API calls)
crier summary
crier summary --json

# Check API keys
crier doctor

# Manual registry management
crier register <file> --platform <platform> [--url <url>]
crier unregister <file> --platform <platform>

# Link content file to registry (fix source_file after temp-file publishing)
crier link <file> --url <canonical_url>
crier link <file>  # uses canonical_url from front matter

Bulk Operations

For large content libraries, use filters to control scope:

# Post 5 random articles to blog platforms (fully automated)
crier audit --publish --yes --only-api --long-form --sample 5

# All missing to API platforms (skips manual/import)
crier audit --publish --yes --only-api

# Include updates to changed content
crier audit --publish --yes --include-changed

# Filter by path - only posts (not projects, papers, etc.)
crier audit content/post --publish --yes --only-api --long-form --sample 5

# Posts from last week
crier audit --since 1w --publish --yes --only-api

# Sample 5 recent posts (last month)
crier audit --sample 5 --since 1m --only-api --long-form

# Fully automated batch mode (implies --yes --json, skips manual)
crier audit --publish --batch --long-form

Filters

• [PATH] — Limit to specific directory (e.g., content/post, content/projects)
• --since — Only content from this date (e.g., 1d, 1w, 1m, 2025-01-01)
• --until — Only content until this date
• --only-api — Skip manual/import/paste platforms
• --long-form — Skip short-form platforms (bluesky, mastodon, twitter, threads)
• --sample N — Random sample of N items
• --include-changed — Also update changed content (default: missing only)

Front Matter Requirements

---
title: "Your Article Title"
canonical_url: "https://yourblog.com/your-article/"
---

The canonical_url is required — it's the article's identity for tracking and linking.

Section Tracking

Crier automatically tracks the content section (e.g., post, papers, projects) for each registered article, inferred from the source file path. This powers the crier summary breakdown by section. No configuration needed.

Important Rules

1. Crier appends the canonical URL to short-form posts automatically. Don't include it in your rewrite text.
2. DevTo tags are auto-sanitized. Hyphens removed, lowercase, max 4 tags. No action needed.
3. Use --yes for non-API modes. This skips interactive prompts that don't work through Claude Code.
4. Ask simple yes/no after manual operations. Trust the user's answer.
5. Show the canonical URL for import-mode platforms. It's the key piece of information.