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 agentmods add commands/rockyco/claude-linkedin-plugin/setupgit clone --depth 1 https://github.com/rockyco/claude-linkedin-pluginWhat 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 | $0.00015 | $0.00600 |
| Opus 5 | $0.00008 | $0.00300 |
| Sonnet 5 | $0.00003 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
setup 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.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn OAuth Setup
Guide the user through setting up LinkedIn API authentication. This is a one-time process.
Step 1: Check existing settings
Read ~/.claude/linkedin.local.md to see if already authenticated. If the file exists and has a valid (non-expired) token, inform the user they are already set up and ask if they want to re-authenticate.
Step 2: LinkedIn Developer App
If the user does not have credentials, walk them through creating a LinkedIn Developer App:
- Tell the user to go to https://www.linkedin.com/developers/apps and click "Create app"
- They need:
- App name (anything descriptive)
- A LinkedIn Company Page to associate with (they can create one if needed)
- App logo
- After creating the app, go to the Auth tab and:
- Copy the Client ID and Client Secret
- Add
http://localhost:9876/callbackas an Authorized redirect URL
- Go to the Products tab and request access to:
- Share on LinkedIn (for w_member_social scope)
- Sign In with LinkedIn using OpenID Connect (for openid and profile scopes)
- Wait for product access to be approved (usually instant for Share on LinkedIn)
Use AskUserQuestion to collect the Client ID and Client Secret from the user.
Step 3: Run OAuth flow
Once you have the client_id and client_secret, run the OAuth server:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/oauth-server.py "<client_id>" "<client_secret>"
This will:
- Print an authorization URL and open the user's browser
- Wait for the OAuth callback on localhost:9876
- Exchange the authorization code for an access token
- Fetch the user's profile and person URN
- Save everything to
~/.claude/linkedin.local.md
Tell the user to authorize the app in their browser when it opens.
Step 4: Verify
After the script completes, read ~/.claude/linkedin.local.md and confirm to the user:
- Their display name
- Their person URN
- Token expiration date (60 days from now)
Tell them they can now use /linkedin:post to publish content.
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.
- 2d ago First seen · 70 lines · 15 tokens per session scan A f37719123c84
setup is a command published in the GitHub repository rockyco/claude-linkedin-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 600 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 commands, from other repositories
linkedin-growth-config
Adjust linkedin-growth account settings — daily invite limit, schedule time, pending threshold, pause/resume — or edit the ICP qualification prompt.
linkedin-growth-status
Show the linkedin-growth dashboard — lead counts by status, invites left today, pending older than the threshold, recent errors, and recent imports.
index-skills
Run the okhp3-skill-cataloger in full index mode to scan root-level family folders and generate SKILLS.md for the distribution surface.
x-post
Draft (or take) a tweet/thread, optionally attach an image, score it against a built-in bookmarkability rubric, preview the cost, and post to X — ONLY after you explicitly confirm. Never auto-publishes. Can also SCHEDULE for later via vibedraft (single posts may carry one image or mp4 video; bulk is text-only)…
log
Use this after you post to LinkedIn. Run /post log to pick a draft, mark it posted, and record likes/comments/shares.
Create a LinkedIn post from any content source.