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.
npx agentmods add instructions/mdbailin/linkedin-content-engine/claude-mdgit clone --depth 1 https://github.com/mdbailin/linkedin-content-engineWrote 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/instructions/mdbailin/linkedin-content-engine/claude-md)<a href="https://agentmods.dev/instructions/mdbailin/linkedin-content-engine/claude-md"><img src="https://agentmods.dev/badge/instructions/mdbailin/linkedin-content-engine/claude-md.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 | $0.01015 | $0.01015 |
| Opus 5 | $0.00508 | $0.00508 |
| Sonnet 5 | $0.00203 | $0.00203 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
linkedin-content-engine CLAUDE.md 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 3d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude implementation brief
You are implementing a production-quality Claude Code plugin and local MCP server called LinkedIn Content Engine.
Goal
Turn a user's content idea into a polished LinkedIn text post or carousel workflow:
- Claude writes the post using the bundled skill and brand profile.
- Claude prepares an image/carousel creative brief.
- The MCP server generates images using OpenAI GPT Image 2.
- Generated assets are uploaded to Cloudinary.
- Carousel slide images are assembled into a PDF when needed.
- The PDF and thumbnail are uploaded to Cloudinary.
- Buffer stores the prepared post as a draft by default.
- Only after explicit user approval may the system add the post to the Buffer queue or schedule a custom publication time.
Architecture constraints
- TypeScript / Node.js.
- Keep API providers behind adapters.
- MCP tools must have narrow, typed schemas.
- Do not let the MCP layer author marketing copy. Claude/the skill is the copywriter.
- Separate pure planning functions from side-effect functions.
- Prefer explicit return values containing IDs, URLs, status, and provider error details.
- Never log secrets or full Authorization headers.
- Never commit
.env. - Mark Buffer-created posts as AI-assisted when the API supports it.
- Default Buffer write action to
saveToDraft: true. - Queue/schedule requires an explicit
approved: trueargument and the skill must ask for approval first. - Support dry-run mode for every side-effecting workflow.
Required MCP tools
Implement these tools (exact names preferred):
read_brand_profile
Loads and validates the active brand profile.
generate_creative
Inputs: creative brief, aspect ratio/size, number of outputs, optional reference asset URLs. Output: local generated file paths + generation metadata. Provider: OpenAI GPT Image 2.
upload_asset
Inputs: local path, asset kind, logical folder, tags. Output: Cloudinary public ID, secure URL, resource type, format, bytes.
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.
- 3d ago First seen · 120 lines · 1,015 tokens per session scan A de8ded5a7f54
linkedin-content-engine CLAUDE.md is an instructions file published in the GitHub repository mdbailin/linkedin-content-engine (0 stars, last pushed 11d ago), licensed MIT. It adds 1,015 tokens to every session, about $0.0051 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 instructions, from other repositories
carousels GEMINI.md
Instructions for sausi-7/carousels: See AGENTS.md for the full pipeline, commands and file shapes.
docvideoer CLAUDE.md
Instructions for coding-ax/docvideoer, covering claude.md — docvideoer, 触发方式, 外部 skill 依赖, 工作目录 and 核心流水线（6 步）.
ai-workflow-kit CLAUDE.md
Claude Code instructions for bezael/ai-workflow-kit, covering claude.md — ai workflow kit, what this repo is, where each tool reads skills from, available skills and specialized agents.
video-mcp CLAUDE.md
Claude Code instructions for Zoean-z/video-mcp, a project described as: 让agent学会理解视频，无需复杂依赖和额外花费.
glm-image-mcp-server CLAUDE.md
Claude Code instructions for ex-takashima/glm-image-mcp-server, covering claude.md - development guide, project overview, build & run commands, install dependencies and build typescript.
ukulele-companion CLAUDE.md
Claude Code instructions for baijum/ukulele-companion, a project described as: An offline app for learning ukulele — on Android and iOS. Chords, scales, music theory, composition tools, and more.