Borrowing it
Nothing to install: this file belongs to tarunkorat/claude-linkedin-post-creator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tarunkorat/claude-linkedin-post-creator/main/.claude/commands/post/generate.mdgit clone --depth 1 https://github.com/tarunkorat/claude-linkedin-post-creatorWrote 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/tarunkorat/claude-linkedin-post-creator/generate)<a href="https://agentmods.dev/commands/tarunkorat/claude-linkedin-post-creator/generate"><img src="https://agentmods.dev/badge/commands/tarunkorat/claude-linkedin-post-creator/generate.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 5.1 | $0.00000 | $0.01134 |
| Opus 5 | $0.00000 | $0.00567 |
| Sonnet 5 | $0.00000 | $0.00227 |
| Haiku 4.5 | $0.00000 | $0.00113 |
Grade A, and why
generate 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 7d 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.
If slack_enabled=true → run the curl command from _shared.md. How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GENERATE
Step 1 — Load context
Run Step 0 from _shared.md. Hold profile data in memory.
topic_hint = any text passed after /post (empty if none).
Step 1B — Read performance history
Read posts/tracker.csv (silently, no output to user).
If the file has 1+ rows with Posted=yes, extract:
- avoid_topics: topics from the 3 lowest-engagement posts (fewest comments) — don't suggest these again
- best_format: format with the highest average comments across all posted rows
- insight: if 5+ rows exist, compute one sentence: e.g. "Story posts average 3x more comments than lists for you."
Hold these as performance_context. If tracker is empty or has no Posted=yes rows, performance_context = null.
Step 2 — Style samples
If SAMPLE_1 in config/profile.md is filled → use those. Skip Chrome navigation.
If all samples are empty → navigate to https://www.linkedin.com/in/me/recent-activity/shares/, read page, extract last 3 post texts. Hold as style_samples.
Step 3 — Research (1 web search + 1 Chrome search)
3A. Web search — 1 query only:
Query: top linkedin posts "<INDUSTRY>" "<primary NICHE_TOPIC>" 2025 OR 2026
Extract from results: hook/first line, post angle or format (story, list, tip, contrarian), engagement signals if shown. Take top 5 results.
3B. Chrome LinkedIn search — 1 query only:
Navigate to:
https://www.linkedin.com/search/results/content/?keywords=<primary_niche_topic_url_encoded>&datePosted=past-month&sortBy=relevance
Read page. Extract: hook, author role, comment count (prefer posts with comments), format. Take 4-5 posts.
3C. Summarize research in 3 lines (internal, don't show user):
- Top formats performing now
- Top topics getting traction
- Hook patterns that appear most
Step 4 — Suggest 3 topics
Using research summary + profile niche/goals + topic_hint + performance_context, generate 3 ideas. If topic_hint given → at least one idea expands it. Skip topics already covered in style_samples. If performance_context is set: skip any idea that overlaps with avoid_topics; prefer best_format for at least one idea.
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.
- 7d ago First seen · 110 lines · 0 tokens per session scan A 08f188a2f277
generate 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 1,134 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.
Other commands, from other repositories
content-pipeline
Run the full multi-agent content production pipeline.
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).
security-scan
Run security audit on codebase.
test-suite
Run comprehensive test suite with coverage analysis.
standardize-claude-md
Add missing toolkit sections (Related Global Rules, Quick Start) to existing CLAUDE.md.
help
Explain Ralph Wiggum technique and available commands.