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.
git 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/post)<a href="https://agentmods.dev/commands/rockyco/claude-linkedin-plugin/post"><img src="https://agentmods.dev/badge/commands/rockyco/claude-linkedin-plugin/post/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/rockyco/claude-linkedin-plugin/post"><img src="https://agentmods.dev/badge/commands/rockyco/claude-linkedin-plugin/post.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00025 | $0.02098 |
| Opus 5.5 | $0.00010 | $0.00839 |
| Sonnet 5.5 | $0.00005 | $0.00420 |
| Haiku 4.5 | $0.00003 | $0.00210 |
Grade A, and why
post 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 1mo 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Post (Local Bundle)
Produce a LinkedIn-ready bundle locally. The user reviews the files and uploads manually via https://www.linkedin.com/feed/?shareActive=true. This command does not call the LinkedIn API.
Follow the linkedin-api skill for 2026-algorithm-optimized content rules (dwell-time hook, 1000-1300 char body, numbered carousel frameworks, no engagement bait, 3-5 hashtags, no em-dashes, no external URLs).
Step 1 - Pick the target directory
Default: <project-root>/docs/linkedin/. Fall back to <project-root>/linkedin/ if docs/ does not exist.
If the working directory does not look like a project root or the location is ambiguous, use AskUserQuestion to confirm.
Create the directory if missing:
mkdir -p "<project>/docs/linkedin"
Step 2 - Decide the format
Default by content type:
- Technical / B2B / explanatory -> PDF document carousel (5-10 slides at 1080x1080). Highest 2026 engagement.
- Opinion, discussion, short take -> text-only
- Announcement / launch with one visual -> single image (1200x627)
If unclear, ask:
What format? options:
1) PDF carousel (5-10 slides, highest engagement, recommended for technical content)
2) Multi-image carousel (2-9 PNGs, similar engagement, quicker to produce)
3) Single image (1200x627, lowest engagement but simple)
4) Text only (short discussion-style post)
Step 3 - Draft and save the post text
Apply every rule from the linkedin-api skill. Summary:
- First 3 lines hook the reader (contrarian, unexpected stat, high-stakes problem, origin, or question)
- Body 1000-1300 chars, 2-3 line paragraphs with white space
- No em-dashes, no "Comment YES" / "DM me" / "link in comment" bait, no polls
- Close with an open question CTA (5+ word reply invited)
- 3-5 hashtags on the last line(s), first tag is the most relevant
Write to <dir>/post.txt:
# Use the Write tool (not bash heredoc) for multi-line text.
Validate:
wc -c <dir>/post.txt # aim for 1000-1300, hard cap 3000
grep -cE '—|–' <dir>/post.txt # em-dash count should be 0
grep -ciE 'comment yes|dm me|follow for more|tag someone|like this post to' <dir>/post.txt # banned bait
grep -cE '^#' <dir>/post.txt # sanity
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.
- 1mo ago First seen · 182 lines · 25 tokens per session scan A dbf20215a91b
post is a command published in the GitHub repository rockyco/claude-linkedin-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 2,098 once invoked, about $0.0001 per session on Opus 5.5. 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
Create a LinkedIn post from any content source.
all
Generate content for all platforms (X, LinkedIn, Medium, Dev.to) from a single input.
learn
Force claude-smart to extract learnings from this session now.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
init
Install the formatters this repository needs, with every command visible before it runs.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.