Claude
Drafting
Project with your last 30 posts as voice anchor. You write the angles (you live them), Claude drafts.
Free · $20/mo Pro · $100/mo Max 5x · $200/mo Ultra · Sonnet API $2/$10 per M tokens (input/output)Alts: ChatGPT
Writing · Personal
LinkedIn (for yourself)
Solo: writing for your own account, not clients.
Drop the multi-client agency tooling. For your own account you don't need Granola interviews or Taplio's viral search. Claude with your own voice library, Typefully to stage and ship, that's it.
· 5 months ago
WRITINGBEGINNERBeginnerFrom $20/mo
The stack
Real monthly cost
small
$20/mo
3 posts/wk
- claude$20
- typefullyFree
medium
$33/mo
Daily + threads
- claude$20
- typefully$13
heavy
$48/mo
Daily + carousels
- claude$20
- typefully$13
- canva$15
Recent changes to this stack
shutdownOCT 30
Fast mode for Claude Opus 4.8 deprecated with November 30 removal date
Fast mode for Claude Opus 4.8 is being deprecated and will be removed on November 30, 2026. Developers using fast mode with Opus 4.8 must migrate to Claude Opus 5.5 to continue using the feature.
featureOCT 29
Usage and Cost Analytics API launched in beta to track token consumption and costs
Anthropic released the Usage and Cost Analytics API in beta, enabling organizations to monitor token usage and costs across Claude API consumption with filtering and grouping by dimensions like model, workspace, and API key. The API provides /v1/organizations/analytics/usage and /v1/organizations/analytics/cost endpoints. Legacy usage reporting endpoints remain supported.
featureOCT 28
Messages API and Token Counting API maximum request size increased to 128 MB
The maximum request size for the Messages API and Token Counting API doubled from 32 MB to 128 MB on the first-party Claude API, allowing developers to process significantly larger payloads in single requests. This change takes effect immediately and applies to both APIs.
featureOCT 28
Substack Notes can now include videos and mentions
Videos up to 15 minutes and @-mentions are now supported in Substack Notes published through Typefully. Videos are automatically preserved when cross-posting from X or LinkedIn, while unsupported content is flagged before publishing.
Workflow
- 1Capture angles in a notes fileClaude
When something happens at work, jot a 1-line angle. You don't need a 30-min interview if you live the work.
- 2Draft posts in batchClaude
Sunday session: feed Claude 5 angles + your voice library, get 5 drafts.
Prompt · Batch draft from your own anglesWrite 5 LinkedIn posts in my voice. Voice library (my last 20 posts): """ {{paste 20 posts}} """ This week's angles (one post per angle): 1. {{angle 1}} 2. {{angle 2}} 3. {{angle 3}} 4. {{angle 4}} 5. {{angle 5}} Constraints per post: - Hook in line 1, no warm-up - 5 to 8 short paragraphs, blank line between - One concrete number, name, or example - No emoji unless my voice library uses them - End on a sharp statement, not a question Output 5 posts separated by "---". - 3Stage in TypefullyTypefully
Paste, schedule across the week. Typefully cross-posts to X if you want a thread version.
What it produced
Solo founder, 4k followers
From posting twice a month to 3x/week. Reach went from ~600 impressions/post to ~3.2k impressions/post over 6 weeks. 11 inbound messages per month from posts alone.
Common pitfalls
AI-flat voice
Without an interview to ground in, drafts drift to generic LinkedIn-speak fast. Keep refreshing the voice library every 4 weeks.
Posting frequency death spiral
Daily posting without batching burns out within a month. Sunday batching (5 posts in 90 min) is the only thing that holds.
Other ways to do LinkedIn ghostwriting
Weekly changelog
What changed in AI tools and the stacks that ship. One email a week.
Spotted something off?
Wrong price, dead link, stale tool — anything. We review every fix.