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 skills add JamalMohafil/claude-skills --skill content-os-buildergit clone --depth 1 https://github.com/JamalMohafil/claude-skillsWrote 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/jamalmohafil/claude-skills/content-os-builder)<a href="https://agentmods.dev/skills/jamalmohafil/claude-skills/content-os-builder"><img src="https://agentmods.dev/badge/skills/jamalmohafil/claude-skills/content-os-builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jamalmohafil/claude-skills/content-os-builder"><img src="https://agentmods.dev/badge/skills/jamalmohafil/claude-skills/content-os-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00248 | $0.05071 |
| Opus 5 | $0.00124 | $0.02535 |
| Sonnet 5 | $0.00050 | $0.01014 |
| Haiku 4.5 | $0.00025 | $0.00507 |
Grade A, and why
content-os-builder 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 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.
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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content OS Builder
You are an AI coding agent (Claude Code, Codex, Kimi, Cursor, or similar) with file-write and shell access. Your job: build the user a personalized content operating system — a local web dashboard that turns idea → plan → produce → publish → learn into one machine, styled and scoped entirely to their brand.
This skill is a playbook, not a fixed template. You will INTERVIEW the user, then GENERATE their OS from the answers. Never hardcode another brand's identity, colors, voice, or topics — everything comes from the interview.
The reference implementation this is distilled from is "jamal-os" (an Arabic applied-AI creator's OS). You are recreating that architecture, reskinned for the current user. If this skill lives inside a repo that already has an
engine/app, you may clone + reskin it instead of building from scratch (see Stage 4).
The golden rule: INTERVIEW FIRST, BUILD SECOND
Do NOT write a single file until the intake interview is complete and the user has confirmed the summary. The whole value is personalization. Skipping the interview produces a generic clone, which is a failure.
Run the interview conversationally (ask in the user's language), accept short answers, offer sensible defaults, and let them say "use defaults for the rest." Then echo a compact summary and get a "yes" before building.
The full question set + the brand-kit.json schema is in references/1-interview.md. The condensed intake (ask all of these) is:
- Identity — brand/creator name, @handle(s), one line on what you do, niche, primary language (+ any secondary), is the primary language RTL (Arabic/Hebrew/Farsi)?
- Audience — who you serve, their level (beginner→pro), the topics/interests you cover.
- Voice — tone/register (formal? casual? a specific dialect?), 2–3 do's, 2–3 don'ts, emoji policy, one or two sample lines that "sound like you."
- Visual identity — primary color, accent color, light or dark default (or both), background feel (flat / gradient / editorial), display font, mono/code font, path to a logo or profile image if any. (Optional: a second palette for print/booklets.)
- Platforms — which platforms, in priority order; which formats you post (Reel, Carousel, Story, YouTube long, Short, Presentation, Post, TikTok…); any custom canvas sizes.
- Strategy — your content pillars and their ratio (e.g. 70% teaching / 20% journey / 10% offer), the 2–4 things you want to be known for (each with a one-line test — this becomes a hard gate on every idea), your funnel stages, your offers, your default CTA, whether it's "one CTA per piece", whether a no-CTA piece is acceptable, and the destination you funnel to (community / product / newsletter).
- Radar — the topics/keywords the trend-radar should scout, the sources/competitors/handles to watch, the daily scan time, and hard filters/no-gos (topics to NEVER touch).
- Grounding & goals — real projects/ventures to ground content in, the proof points you can actually stand behind (the only things the AI may cite), anything you've retired and never want repeated, and the goal metric (followers, subs, revenue).
- Analytics & competitors (the "never open the app again" layer — optional but high value) — do you want your own posts + insights + comments pulled in? Which accounts (Instagram Business/Creator? YouTube channel?). Do you have (or can you create) a Meta app + IG Business account, a YouTube API key, an OpenAI key for transcription? Which competitors/creators do you want to study? Should transcription use free YouTube captions where available (cheaper) or always OpenAI?
- Ops — package manager (pnpm/npm), does your agent have shell access + can run a local dev server, can your agent invoke itself headlessly (a
claude --print-style CLI a Node process canspawn— this decides whether generation runs automatically or falls back to prompt-handoff), is there a scheduler available (cron/launchd/Task Scheduler), any connectors to wire (Notion, Buffer — optional), and do you want the OS to draft/schedule posts or just hand you the assets (default)? Either way state the rule back: nothing is ever posted to a live account without an explicit go-ahead at that moment.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- README.md 6.6 KB
- references/1-interview.md 12 KB
- references/2-brand-and-design.md 4.9 KB
- references/3-dashboard-app.md 27 KB
- references/4-builders-and-export.md 8.2 KB
- references/5-radar-and-calendar.md 14 KB
- references/6-analytics-and-inspiration.md 14 KB
- references/7-core-libs.md 20 KB
- references/8-publish-and-growth.md 18 KB
- references/9-assistant-chat.md 14 KB
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 Changed · +2 lines 3390f854fec0
- 5d ago Changed · +2 lines 8a184cd18119
- 6d ago First seen · 143 lines · 248 tokens per session scan A e16385f4dfaa
content-os-builder is a skill published in the GitHub repository JamalMohafil/claude-skills (25 stars, last pushed 4d ago), licensed MIT. It adds 248 tokens to every session and 5,071 once invoked, about $0.0012 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 2026-09-04.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.