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 skills/robinsadeghpour/content-workflow/setupnpx skills add robinsadeghpour/content-workflow --skill setupgit clone --depth 1 https://github.com/robinsadeghpour/content-workflowWhat 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 | $0.00064 | $0.01299 |
| Opus 5 | $0.00032 | $0.00649 |
| Sonnet 5 | $0.00013 | $0.00260 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade D, and why
setup scanned grade D with 2 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 2d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls .claude/skills/ | grep -E "apify-ultimate-scraper|humanizer|nano-banana|supadata|postiz" Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/apify-skills How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup
You are guiding the user through one-time setup of the content workflow. This is a fresh-clone install: third-party skills, environment file, and dependency check.
Steps
Walk through each section in order. Stop and ask the user at the checkpoints before continuing — don't blow through everything silently.
1. Confirm working directory
Verify you're at the repo root:
pwd && ls package.json .claude/ 2>&1
If not at the repo root, stop and tell the user to cd into the cloned repo.
2. Check prerequisites
Run these checks in parallel and report results:
node --version # need 20+
python3 --version # need 3.10+
which claude # need Claude Code CLI installed
If any are missing, point the user at the README's Setup section and stop.
3. Install Node dependencies
npm install
This pulls better-sqlite3, canvas, sharp, node-cron, etc. Canvas needs Cairo system libs on macOS — if install fails, run brew install pkg-config cairo pango libpng jpeg giflib librsvg and retry.
4. Create .env from template
Check if .env already exists:
test -f .env && echo "exists" || echo "missing"
If missing, copy the template:
cp .env.example .env
Then stop and tell the user to fill in the API keys before continuing. Show them which keys are which:
ANTHROPIC_API_KEY— only needed if scripts call the SDK directly; Claude Code uses your CLI authAPIFY_TOKEN— required for trend scraping (sign up: https://apify.com)SUPADATA_API_KEY— required for video transcripts (sign up: https://supadata.ai/?ref=robin)GEMINI_API_KEY— required for nano-banana fallback images (sign up: https://aistudio.google.com/apikey)POSTIZ_API_KEY— required to actually schedule posts (sign up: https://postiz.pro/robin-sadeghpour-faraj)
Checkpoint: Wait for the user to confirm .env is filled in (or that they'll do it later). Then continue.
5. Install third-party skills
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.
- 2d ago First seen · 131 lines · 64 tokens per session scan D f224a8d7b31e
setup is a skill published in the GitHub repository robinsadeghpour/content-workflow (55 stars, last pushed 3mo ago), licensed MIT. It adds 64 tokens to every session and 1,299 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 2 findings (enumerates other installed skills, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…