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/robinsadeghpour/content-workflow/claude-mdgit clone --depth 1 https://github.com/robinsadeghpour/content-workflowWrote 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/robinsadeghpour/content-workflow/claude-md)<a href="https://agentmods.dev/instructions/robinsadeghpour/content-workflow/claude-md"><img src="https://agentmods.dev/badge/instructions/robinsadeghpour/content-workflow/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 | $0.05125 | $0.05125 |
| Opus 5 | $0.02563 | $0.02563 |
| Sonnet 5 | $0.01025 | $0.01025 |
| Haiku 4.5 | $0.00513 | $0.00513 |
Grade A, and why
content-workflow CLAUDE.md 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| `zx` | 8.x (`@lite` variant) | Shell orchestration in JS scripts | Wrapping multi-step pipeline calls (scrape → generate → overlay → schedule) in a readable async script without raw `child_process`. ~7x smaller than fu How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project
Content Workflow
A Claude Code-native content automation system that handles the full pipeline from idea discovery to scheduled publishing across LinkedIn, TikTok (EN + DE), and Instagram. Built with skills, agents, and cron automation to let Robin review and approve content in a single morning batch while the system handles research, drafting, media generation, and scheduling via Postiz.
Core Value: One morning session turns a curated idea backlog into platform-native content scheduled across all channels — no context-switching, no manual formatting, no copy-pasting between tools.
Constraints
- Tech stack: Claude Code skills + agents as primary architecture, Node.js scripts where needed (Larry pipeline)
- Publishing: All scheduling through Postiz API
- Language: English master content, German localization for TikTok DE only
- Human-in-the-loop: No post publishes without Robin's explicit approval
- Voice: Must sound authentically Robin — LinkedIn slightly formal but real, TikTok/Instagram casual ("brooo", "bruh" energy)
- Media priority: Real visuals (logos, screenshots, product images) preferred over AI-generated imagery
Technology Stack
Recommended Stack
Core Technologies
| Technology | Version | Purpose | Why Recommended |
|---|---|---|---|
| Node.js | 20+ LTS | Runtime for all scripts | Larry pipeline is already Node.js; Claude Code skills invoke bash which calls node scripts. Ecosystem depth for image, HTTP, file I/O is unmatched. |
@anthropic-ai/sdk |
0.85.0 | Content generation, translation, humanizer calls | Native to the Claude Code environment. Used in-process for text generation, translation of EN→DE, voice calibration. Current latest as of research date. |
@postiz/node |
1.0.8 | Scheduling + cross-platform publishing | Already integrated as a skill. Official SDK. Supports LinkedIn, TikTok, Instagram, 28+ platforms. Also exposes analytics API needed for feedback loop. Rate limit: 30 req/hr (non-posting). |
canvas (node-canvas) |
2.x | Slide text overlay compositing | Larry 1.0.0 already ships this as add-text-overlay.js. Cairo-based, ~800K weekly downloads, longest track record, most compatible with browser Canvas2D API. The existing codebase uses createCanvas + loadImage from this package — no migration cost. |
sharp |
0.34.5 | Image resize, format conversion, composite assembly | Fastest Node.js image processor (libvips). Used for final slide compositing, logo/screenshot scaling, format conversion (PNG→WebP for Instagram). Text is rendered via canvas, then composited via sharp for output. |
playwright (Python CLI) |
1.x (Playwright sync) | HTML→slide screenshot pipeline | The existing linkedin skill's screenshot-slides.py already uses playwright.sync_api. This is the proven path: Claude writes HTML, Playwright renders and captures each .slide element at 2x DPR. Do not replace this. |
node-cron |
4.2.1+ | Daily pulse cron trigger | 3M weekly downloads, minimal API, zero dependencies, full cron syntax. Used for 0 6 * * * daily pulse and 0 20 * * * end-of-day performance check. |
better-sqlite3 |
latest | Idea backlog, performance history, voice profile cache | Fastest synchronous SQLite for Node.js. Single-user CLI context — sync API is ideal (no callback complexity). Outperforms lowdb by orders of magnitude once rows exceed ~1K. Stores: content ideas, post metadata, performance scores, scrape dedup hashes. |
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.
- 4d ago First seen · 199 lines · 5,125 tokens per session scan A fd3f0853bca3
content-workflow CLAUDE.md is an instructions file published in the GitHub repository robinsadeghpour/content-workflow (55 stars, last pushed 3mo ago), licensed MIT. It adds 5,125 tokens to every session, about $0.0256 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.