panguard-ai: Command for Claude Code

.claude/commands/write-linkedin.md

write-linkedin is a command for Claude Code from panguard-ai/panguard-ai. It costs 0 tokens per session (368 once invoked), scanned A, original, MIT.

A LinkedIn-post writing command for Panguard AI’s company page or founder profile. LinkedIn is a professional social network.

In plain words
What is it for?
Use it to create a 1,200–1,500-character post with a hook, short paragraphs, a closing question, and relevant hashtags.
Why use it?
It gives a topic or blog post a consistent structure and business-focused tone suited to decision-makers, without requiring the writer to plan the format from scratch.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is panguard-ai/panguard-ai's own configuration. It tells Claude Code how to work on panguard-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything panguard-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to panguard-ai/panguard-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/panguard-ai/panguard-ai/main/.claude/commands/write-linkedin.md
Clone the repo
git clone --depth 1 https://github.com/panguard-ai/panguard-ai

Made for: Claude Code.

Wrote 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.

agentmods badge for write-linkedin

README.md
[![agentmods](https://agentmods.dev/badge/commands/panguard-ai/panguard-ai/write-linkedin/github.svg)](https://agentmods.dev/commands/panguard-ai/panguard-ai/write-linkedin)
Your own site
<a href="https://agentmods.dev/commands/panguard-ai/panguard-ai/write-linkedin"><img src="https://agentmods.dev/badge/commands/panguard-ai/panguard-ai/write-linkedin/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.

agentmods 80×15 button for write-linkedin

Your own site · 80×15
<a href="https://agentmods.dev/commands/panguard-ai/panguard-ai/write-linkedin"><img src="https://agentmods.dev/badge/commands/panguard-ai/panguard-ai/write-linkedin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 368 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00368
Opus 5 $0.00000 $0.00184
Sonnet 5 $0.00000 $0.00074
Haiku 4.5 $0.00000 $0.00037

Measured 9d ago against content hash 74ac973403d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

write-linkedin 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 9d 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.

.claude/commands/write-linkedin.md · 44 lines

What it actually says

/write-linkedin — Generate LinkedIn Post for Panguard AI

You are writing a LinkedIn post for Panguard AI's company page or founder's personal profile.

Input

The user provides a topic, or reference an existing blog post to adapt.

LinkedIn Post Format

  • 1,200-1,500 characters (optimal for engagement)
  • First line: hook (question, stat, or bold statement) — this is what shows before "see more"
  • Body: 3-5 short paragraphs, single-spaced with blank lines between
  • Include line breaks for readability
  • End with a question to encourage comments
  • No emojis
  • 3-5 relevant hashtags at the bottom

Tone

  • More professional than Twitter, less technical
  • Speak to CTOs, IT managers, startup founders
  • Focus on business impact, not just tech specs
  • Storytelling format works well ("Last month, a 3-person startup...")

Content Angles

  1. Thought leadership — Why AI security matters for SMBs
  2. Product announcement — New feature, milestone, benchmark
  3. Industry insight — Threat landscape, compliance changes
  4. Open source story — Community growth, ATR contributions
  5. Hiring/culture — If applicable

Brand Context

  • Panguard AI: AI-powered endpoint security, CLI-first
  • Target: developers, SMBs, startups without security teams
  • Differentiator: installs in 60 seconds, open source ATR rules, 3-tier AI funnel
  • Pricing: Free tier with real value (not just a trial)

Output

Return the post in a code block. Include suggested posting day/time (Tue-Thu 8-10am work best on LinkedIn).

Changes

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.

  1. 9d ago First seen · 44 lines · 0 tokens per session scan A 74ac973403d9

Subscribe to this mod's changes

write-linkedin is a command published in the GitHub repository panguard-ai/panguard-ai (63 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 368 tokens. 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 2026-08-30.