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/commentsgit clone --depth 1 https://github.com/rockyco/claude-linkedin-pluginWrote 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/commands/rockyco/claude-linkedin-plugin/comments)<a href="https://agentmods.dev/commands/rockyco/claude-linkedin-plugin/comments"><img src="https://agentmods.dev/badge/commands/rockyco/claude-linkedin-plugin/comments.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.00962 |
| Opus 5 | $0.00006 | $0.00481 |
| Sonnet 5 | $0.00002 | $0.00192 |
| Haiku 4.5 | $0.00001 | $0.00096 |
Grade A, and why
comments 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 3d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Comments
View comments on a LinkedIn post and reply to them.
Prerequisites
The comments API uses LinkedIn's socialActions endpoint which requires the Community Management API product (partner-level access). The basic "Share on LinkedIn" product (w_member_social) does NOT grant access to these endpoints.
If the user hasn't applied for Community Management API access, the API commands will fail with 403. In that case, inform the user and suggest they interact with comments via LinkedIn's website.
Step 1: Check authentication
Run this to verify credentials:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/linkedin-api.py check-auth
If it fails, tell the user to run /linkedin:setup first.
Step 2: Determine the post URN
The user needs to provide a post URN (e.g. urn:li:ugcPost:123 or urn:li:share:456).
If the user says "latest" or doesn't specify, check if there's a recent post URN from the current session. If not, ask the user for the post URN - they can find it from a previous /linkedin:post output or from the LinkedIn URL of the post.
Step 3: Try to list comments
Try listing comments via the API:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/linkedin-api.py list-comments --post-urn "POST_URN_HERE"
If listing succeeds: Display comments in a readable format with numbering, text, timestamp, and comment URN for each.
If listing fails (403 - expected for most users): The r_member_social scope required for reading comments is restricted to select API partners. Tell the user:
- They can view comments on LinkedIn's website
- The user can provide the comment URN from LinkedIn's web interface if they want to reply
- Creating new top-level comments still works without this scope
Step 4: Handle user actions
Use AskUserQuestion to ask the user what they want to do:
- Reply to a specific comment (user must provide comment URN if listing failed)
- Add a new top-level comment
- Done / exit
Reply to a comment
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.
- 3d ago First seen · 103 lines · 12 tokens per session scan A 28a3ec18b2fc
comments is a command published in the GitHub repository rockyco/claude-linkedin-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 962 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
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)…
post
Compose and publish a post to X (Twitter).
setup
Set up X (Twitter) API authentication (OAuth 2.0 with PKCE).
status
Check X (Twitter) authentication status and token health.
Create a LinkedIn post from any content source.
all
Generate content for all platforms (X, LinkedIn, Medium, Dev.to) from a single input.