_shared

_shared is a command for Claude Code from tarunkorat/claude-linkedin-post-creator. It costs 0 tokens per session (520 once invoked), scanned A, original, MIT.

Shared startup instructions for a set of LinkedIn posting workflows. They read profile settings, check Chrome and LinkedIn access, and define how drafts are saved.

In plain words
What is it for?
Use them when preparing LinkedIn posts, checking the active profile, saving dated drafts, or sending draft notifications to Slack.
Why use it?
They give related posting commands the same profile, date, login, and notification checks.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/tarunkorat/claude-linkedin-post-creator/_shared
Clone the repo
git clone --depth 1 https://github.com/tarunkorat/claude-linkedin-post-creator

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 _shared

README.md
[![agentmods](https://agentmods.dev/badge/commands/tarunkorat/claude-linkedin-post-creator/_shared.svg)](https://agentmods.dev/commands/tarunkorat/claude-linkedin-post-creator/_shared)
Your own site
<a href="https://agentmods.dev/commands/tarunkorat/claude-linkedin-post-creator/_shared"><img src="https://agentmods.dev/badge/commands/tarunkorat/claude-linkedin-post-creator/_shared.svg" alt="Measured on agentmods" 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 520 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00000 $0.00520
Opus 5 $0.00000 $0.00260
Sonnet 5 $0.00000 $0.00104
Haiku 4.5 $0.00000 $0.00052

Measured 4d ago against content hash 2b1d8076d1eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

_shared scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -o /dev/null -w "%{http_code}" -X POST "WEBHOOK_URL" \
.claude/commands/post/_shared.md · 50 lines

What it actually says

Shared — loaded by all /post flows

Today's date: read from system (YYYY-MM-DD).

Step 0 — Startup checks

0A. Read config/profile.md

Extract: NAME, ROLE, INDUSTRY, NICHE_TOPICS, AUDIENCE, TONE, FORMAT, VOICE, POST_LENGTH, EMOJI_USAGE, HASHTAG_COUNT, AVOID, GOALS, SAMPLE_1/2/3. If NAME is empty → stop: "Run /post sync first to fill in config/profile.md, or edit it manually."

0B. Read config/slack.md

If WEBHOOK_URL is not "YOUR_WEBHOOK_URL" → slack_enabled=true. Else slack_enabled=false.

0C. Chrome check

Call mcp__Claude_in_Chrome__tabs_context_mcp (createIfEmpty:true). Fail → stop: "Chrome not connected." Create a new tab. Navigate to https://www.linkedin.com/in/me/. Read page. Redirected to login → stop: "Log in to LinkedIn in Chrome first." Success → print: ✓ Chrome · LinkedIn: <name>

Output

Save draft to: posts/draft_YYYY-MM-DD_<2-3-word-slug>.md

File format:

# <Topic>
Date: YYYY-MM-DD | Topic: <topic> | Why: <one sentence>

---
<post text>
---

Slack (if slack_enabled=true):

curl -s -o /dev/null -w "%{http_code}" -X POST "WEBHOOK_URL" \
  -H "Content-Type: application/json" \
  -d "{\"text\": \"*LinkedIn Draft*\n\n<escaped post text>\n\n_File: posts/draft_<slug>.md_\"}"

Non-200 → warn user, draft already saved locally.

Post writing rules

  • No em-dashes (—). Scan before output.
  • Mirror TONE, FORMAT, VOICE, POST_LENGTH, EMOJI_USAGE, HASHTAG_COUNT from profile.
  • First line = scroll-stopping hook. Specific, direct, or surprising.
  • No filler openers: "In today's world", "As a software engineer", "Hot take:", "I've been thinking about".
  • No AI phrases: "delve", "it's worth noting", "the importance of".
  • End with a genuine question or CTA.
  • Hashtags on their own line at the end.
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. 4d ago First seen · 50 lines · 0 tokens per session scan A 2b1d8076d1eb

Subscribe to this mod's changes

_shared is a command published in the GitHub repository tarunkorat/claude-linkedin-post-creator (6 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 520 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.