Borrowing it
Nothing to install: this file belongs to deepshal99/notch-so-good. 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/deepshal99/notch-so-good/main/.agents/skills/linkedin-content/SKILL.mdgit clone --depth 1 https://github.com/deepshal99/notch-so-goodWrote 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/skills/deepshal99/notch-so-good/linkedin-content)<a href="https://agentmods.dev/skills/deepshal99/notch-so-good/linkedin-content"><img src="https://agentmods.dev/badge/skills/deepshal99/notch-so-good/linkedin-content.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 | $0.00093 | $0.02236 |
| Opus 5 | $0.00046 | $0.01118 |
| Sonnet 5 | $0.00019 | $0.00447 |
| Haiku 4.5 | $0.00009 | $0.00224 |
Grade A, and why
linkedin-content 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 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.
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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Content
Write high-engagement LinkedIn posts via inference.sh CLI.
Quick Start
Requires inference.sh CLI (
infsh). Get installation instructions:npx skills add inference-sh/skills@agent-tools
infsh login
# Research trending LinkedIn content patterns
infsh app run tavily/search-assistant --input '{
"query": "LinkedIn viral post examples 2024 high engagement patterns"
}'
# Post to X (cross-posting reference)
infsh app run x/post-create --input '{
"text": "Your cross-posted version here"
}'
Post Anatomy
┌─────────────────────────────────────┐
│ HOOK (first 1-2 lines) │ ← Visible before "...see more"
│ │
│ ...see more ─────────────────────── │ ← The click gate
│ │
│ BODY (story/value) │
│ - Formatted with line breaks │
│ - Short paragraphs (1-2 sentences) │
│ - Lists or numbered points │
│ │
│ CTA (last 1-2 lines) │ ← Ask for engagement
│ │
│ #hashtags (3-5) │
└─────────────────────────────────────┘
Character Limits
| Element | Limit |
|---|---|
| Post text | 3,000 characters |
| Visible before "see more" | ~210 characters (~2 lines on mobile) |
| Hashtags | 3-5 recommended |
| Comment | 1,250 characters |
| Article title | 100 characters |
| Article body | 125,000 characters |
The first 210 characters are everything. If the hook fails, nobody clicks "see more."
Hook Formulas
What Works
| Formula | Example |
|---|---|
| Contrarian opinion | "Unpopular opinion: code reviews are a waste of time." |
| Personal story opening | "I got fired on a Tuesday. Best thing that ever happened." |
| Surprising stat | "92% of startups fail. But not for the reason you think." |
| List promise | "I've hired 200+ engineers. Here are 5 red flags I look for." |
| Bold statement | "Your resume doesn't matter. Here's what does." |
| Before/after | "3 years ago I couldn't get a single interview. Yesterday I turned down a FAANG offer." |
| Pattern interrupt | "Stop. Before you send that cold email, read this." |
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 · 234 lines · 93 tokens per session scan A ad68a44e8d24
linkedin-content is a skill published in the GitHub repository deepshal99/notch-so-good (7 stars, last pushed 25d ago), licensed MIT. It adds 93 tokens to every session and 2,236 once invoked, about $0.0005 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 skills, from other repositories
lights-hooks
Install Lights traffic-light status hooks into Claude Code's settings.json. Lights is a macOS menu-bar app that shows AI activity as a floating traffic light (red=executing, yellow=needs input, green=idle). Use this skill when the user mentions Lights, asks how to connect Lights to Claude Code, says "set up lights…
claudexor
Use the local Claudexor control plane for harness-agnostic coding work across Claude Code, Codex, Cursor, and OpenCode. Use when a task benefits from route-aware harness and account selection, quota-aware account rotation, shared thread context, read-only planning or research, best-of-N execution, or cross-harness…
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.
cross-campaign
Discover and reference other camps, projects, and files across camp boundaries. Use when the user mentions another camp or campaign by name, references work done "in another project/camp", or needs to find/copy/compare code across camps.
dashiai-ppt
A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.
xiaohongshu-image-creator
An image-making assistant for Xiaohongshu, a Chinese social platform for lifestyle, product, and educational posts. It creates vertical covers and supporting images matched to the post’s topic, audience, and visual style.