LinkedIn posts with Claude Code and Bolta
Turn your repo's release notes into social drafts, from the terminal. Parts of the Claude Code route are not confirmed yet, and the note below says which. Nothing goes live on LinkedIn until you say yes.
Partly confirmed, see what is and is notChecked 2026-11-21
Two slash commands, then a browser sign-in. You tick the brands Claude Code may reach.
How did my recent LinkedIn posts do, and what should I post next? Read only, change nothing.
Illustration of the reply: Bolta returns a draft showing the connected account and the scheduled time, with Approve, Edit and Reject actions.
What is and is not confirmed
Read this before you set up Claude Code
- Confirmed in Claude Code's official docs: remote HTTP MCP servers with browser sign-in through /mcp, skills as SKILL.md folders, and plugin marketplaces added from a GitHub repo.
- Bolta's own plugin is the most tested path. A full real-world run on every setup is still beta (plugin v0.5.3).
- Not confirmed here: the exact minimum Claude Code version for plugin marketplaces (the Bolta plugin README names 2.1.295 or later only as an example), and running Bolta end to end from claude -p in scripts. Claude Code's docs say headless runs cannot do the browser sign-in. The API key header route follows Claude Code's documented --header option but was not run end to end.
What Bolta does on LinkedIn
Bolta writes the text, saves it as a draft on the account you name, and waits. Bolta lists each LinkedIn organization as its own account, so a company page is a separate choice from your personal profile.
- Text posts to a personal profile or to a company page you have connected.
- Posts visible to everyone by default, or to connections only if you ask for that.
LinkedIn limits and format rules
Network rules last checked 2026-07-28. Bolta's posting rules for your workspace (get-posting-rules) win if they differ from this page.
Not promised for LinkedIn from Claude Code: LinkedIn articles, newsletters and document carousels. LinkedIn supports them, but this page does not confirm that Bolta publishes them. Comment length limits. The one checked limit on this page is the feed post.
| What to know | LinkedIn's own rule | What Bolta does |
|---|---|---|
| Post length | A feed post is capped at 3,000 characters, counting spaces, line breaks, emoji and the full text of any link you paste. | Bolta does not check LinkedIn text length, so LinkedIn may refuse longer text. The draft has to fit before you say yes. |
| Opening lines | The feed cuts a post after the first few lines behind a see more link. | Bolta keeps your first lines as written. Put the point there. |
| Formatting | Not stated on this page. | Plain text only. Bold, italic and headings become look-alike characters, a list becomes bullets, and a link is written as label (url). #hashtags and @mentions are kept as typed. |
| Who can see it | Not stated on this page. | Everyone, unless you set the post to connections only. |
Claude Code jobs for LinkedIn, and how to write them
- Draft launch posts from a README section before you push a release
- Draft a week of build-in-public posts in your own voice between coding sessions
- Write to 3,000 characters including spaces, line breaks, emoji and any pasted link, because Bolta will not stop a post that is too long.
Example prompts for LinkedIn
Things to type in Claude Code. Each one asks for a draft and shows you the text first.
How did my recent LinkedIn posts do, and what should I post next? Read only, change nothing.
Summarise what the last merged pull request changed in two plain sentences for customers, then save it as a LinkedIn draft.
Read the top entry in CHANGELOG.md and save a LinkedIn draft about it for my review
Look at the last five commits and draft a LinkedIn post about what changed, without markdown
Bolta saves a draft, you read the exact text, you say yes
- 01
Bolta saves a draft
Claude Code asks Bolta for the LinkedIn post in your brand voice (save-post). A saved draft is never public.
- 02
You read the exact text
On LinkedIn the exact text includes where the line breaks fall, because the feed hides everything after the first few lines, and how any formatting was flattened to plain text.
- 03
You say yes
Only then does Bolta schedule or publish (publish-post), in your workspace's timezone. Safe Mode, client sign-off and brand approval rules still apply.
Using Claude Code for LinkedIn
Parts of this route are not confirmed. The note above says which.
For LinkedIn, Claude Code, from Anthropic, reaches Bolta through Plugin from the bolta-skills marketplace, or claude mcp add. Sign-in: Sign in (OAuth) from /mcp. The LinkedIn account itself is connected inside Bolta, not in Claude Code.
Claude Code is a terminal coding agent, so the natural LinkedIn job is turning a changelog, README or release notes already in your repo into a draft. Bolta's plugin for it bundles the connection and a skill.
An illustration from the Claude Code guide, not real output. You ask: Summarise what the last merged pull request changed in two plain sentences for customers, then save it as a LinkedIn draft. The reply goes along these lines: I read the pull request description and the changed files, using git or the GitHub CLI if it is installed here, then wrote a short customer-facing summary. It is saved in Bolta as a draft and shown below in full. If a detail in the summary is a guess on my part, I flag it so you can correct it before anything moves. Draft saved. Waits for your yes.
An illustration from the Claude Code guide, not real output. You ask: Which Bolta brands can you see, and which accounts are connected to each? Do not change anything. The reply goes along these lines: These are the brands you ticked when you signed in, with their connected networks listed under each. If a brand is missing, run /mcp, pick Bolta and sign in again to tick it. Read only. Nothing changed.
The optional bolta-checks plugin shows a check before anything public or final, such as posting, replying, approving, scheduling, running a routine now or starting a campaign. Saving drafts needs no check. On Windows it needs Git for Windows, because the checks use sh and awk and every Bolta save is blocked without them.
Claude Code's docs describe adding a static key with --header "Authorization: Bearer <token>", or putting it under headers in .mcp.json with ${VAR} expansion. Bolta supports API keys, so that route should work, but it was not run end to end for this page.
Prefer sign-in. Posts from a sign-in are held as AI drafts for review, and a pasted Bolta API key skips that hold.
- Write a batch of drafts. Ask for several posts at once, such as a week of build-in-public notes, and review them together.
- Read results. Check how recent posts and accounts performed so the next draft is informed by it. Read only.
- Read the source in your project. Claude Code opens the file you named, such as CHANGELOG.md or a README section. This step is Claude Code's own, and Bolta is not involved yet.
- Save the draft and show it. Each draft is saved, free, as an AI draft and printed in the terminal in full. Nothing is scheduled.
- Setup: Sign in from /mcp. Run /mcp, select Bolta and choose sign in. Your browser opens on bolta.ai. Sign in, pick your organization and tick the brands this connection may reach. There is no key to copy.
- Setup: Paste the address if the browser errors. If the browser shows a connection error at the end, copy the full address from the address bar and paste it into the prompt Claude Code shows. Then go back to the terminal.
- MCP with an API key header. Claude Code documents --header and .mcp.json headers, and Bolta accepts keys starting with bolta_sk_. We have not run it end to end. A pasted key skips the AI-draft hold.
- Routine output lands in Bolta's inbox for review. Open Claude Code later and list it with list-inbox-items.
- Install the plugin. In the Claude Code prompt, run /plugin marketplace add boltaai/bolta-skills, then /plugin install bolta@bolta-marketplace.
Connect Claude Code to Bolta
Two slash commands, then a browser sign-in. You tick the brands Claude Code may reach.
LinkedIn questions, answered for Claude Code
- How long can a LinkedIn post be when it comes from Claude Code?
- A LinkedIn feed post is capped at 3,000 characters, and the count includes spaces, line breaks, emoji and the full text of any link you paste. Bolta does not check LinkedIn length, so Claude Code should write inside the limit and show you the final text before you say yes.
- Can Claude Code post to a LinkedIn company page and not only my profile?
- Bolta lists each LinkedIn organization as its own account, so you can name the page when you ask (list-accounts). The company page has to be connected in Bolta first. If it is not there, ask for a connect link (get-connect-link) and finish the sign-in in your browser.
- What is Claude Code, and how is it different from Claude or Claude Cowork?
- Claude Code is Anthropic's coding agent that runs in your terminal and reads your project files. Claude is the chat app, and Cowork and Duet have their own Bolta pages. Bolta behaves the same in all of them: drafts are free and nothing publishes without your yes.
- Can I use Bolta from a script or CI with Claude Code?
- Claude Code documents a --header option and .mcp.json headers for static keys, and Bolta supports API keys. Its docs also say claude -p runs cannot do the browser sign-in, so you would sign in first from an interactive session. We have not run Bolta end to end from claude -p or CI, so test it yourself and prefer sign-in for anything a person reviews.
- Can my whole team share one Bolta setup through the repo?
- Claude Code's project scope writes a .mcp.json file you can commit, and each person approves it and signs in as themselves. Their Bolta role decides what they can do, so a shared file never shares one person's permissions.
- A brand I expect is missing.
- It was not ticked at sign-in, or you added it afterwards. Run /mcp, pick Bolta, sign in again and tick it. If you ticked several brands, name the one you mean in your request.
- Does Claude Code publish LinkedIn posts without my yes?
- No. Nothing is approved, scheduled or published until you say yes to that LinkedIn post. Whether Claude Code completes the connection is not fully confirmed, so read the note above first.
More from Claude Code
Claude Code can work with the other networks Bolta publishes to. Each page has its own limits and review notes.
LinkedIn from other AI agents
The same LinkedIn limits apply whichever agent asks. The connection and the setup are what change.
Try a LinkedIn draft from Claude Code
Connect Claude Code, ask for a LinkedIn draft and read the exact text. Nothing goes live until you say yes.