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 khasky/awesome-agent-skills --skill awesome-content-campaigngit clone --depth 1 https://github.com/khasky/awesome-agent-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/khasky/awesome-agent-skills/awesome-content-campaign)<a href="https://agentmods.dev/skills/khasky/awesome-agent-skills/awesome-content-campaign"><img src="https://agentmods.dev/badge/skills/khasky/awesome-agent-skills/awesome-content-campaign/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/khasky/awesome-agent-skills/awesome-content-campaign"><img src="https://agentmods.dev/badge/skills/khasky/awesome-agent-skills/awesome-content-campaign.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 | $0.00170 | $0.11882 |
| Opus 5 | $0.00085 | $0.05941 |
| Sonnet 5 | $0.00034 | $0.02376 |
| Haiku 4.5 | $0.00017 | $0.01188 |
Grade A, and why
awesome-content-campaign 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 today.
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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Campaign
Turn raw product knowledge into a batch of dated, platform-fit posts a publisher (human or awesome-content-publisher) can ship on schedule. The pipeline: ingest sources → knowledge map → interview → live platform research → schedule and media → write to genre and voice → two-stage self-audit → files + manifest. The author's voice is not built here: question 9 points at a profile from awesome-content-voice, and a campaign without one still runs on the voice chosen in the interview.
Core principle: every claim in every post traces to the knowledge map, and every map entry traces to a source. A post may persuade, but it may not invent — no fabricated numbers, testimonials, user counts, benchmarks, or "coming soon" features the sources do not support. A claim that cannot be verified is dropped or explicitly flagged to the user, never smoothed into fluent copy. The second principle: the posts must read human — the self-audit phase is not optional. The third: every post markets the product — it carries the campaign's primary link (or the platform's equivalent CTA where caption links are dead), placed where it reads as the natural next step of the post, never as an ad stamp. A post that delivers value but never touches the product is filler; a post that is only the link is spam; the craft lives in the span between.
Bundled files (load on demand):
references/platforms.md— the canonical platform vocabulary: the slug table with the target detail each platform needs, which platforms cannot post without media, and which genre file governs its register — plus structural notes per platform and the checklist of volatile limits to verify live. Deliberately carries no character-cap numbers; those rot, and Phase 3 fetches them fresh.awesome-content-publisherparses against this same table, so a platform is added here once, never restated in a SKILL.md.scripts/check-campaign.mjs(Node 18+, no dependencies) — the output gate: parses every filename back against the Phase 4 contract, checks frontmatter against the filename it sits next to, catches slot collisions, missing attachments, placeholders and same-platform duplicate bodies. Reads the slug table fromreferences/platforms.md, so the vocabulary lives in one file.--self-testproves each check can fail before it is trusted to pass anything.references/genre-micro-post.md,references/genre-long-article.md,references/genre-community-post.md— register per genre: the human baseline, the AI tells that genre produces, and the rules Phase 5 writes against. Each platform's genre is named in the table above; load only the ones the campaign selected.
Images are not made here. awesome-content-graphics owns that stage whole — the look inputs, the variant set, the headline gate and the pick gate — and Phase 4 calls the Skill tool with "awesome-content-graphics" instead of carrying its own copy of the rules. This skill supplies the facts and the boundary, and records the two answers the user gave it.
What ships with it
5 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.
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.
- today Changed f1ec6c7f982b
- 2d ago Changed · +25 lines 16ddfe1aeeed
- 3d ago Changed c673922d836b
- 5d ago Changed · -64 tokens per session 4050ad6c5ce9
- 7d ago Changed · +34 lines · +3 tokens per session 492285261ea9
- 11d ago First seen · 239 lines · 231 tokens per session scan A 324697c593b7
awesome-content-campaign is a skill published in the GitHub repository khasky/awesome-agent-skills (8 stars, last pushed yesterday), licensed MIT. It adds 170 tokens to every session and 11,882 once invoked, about $0.0009 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
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…
9router-web-fetch
Fetch URL → markdown / text / HTML via 9Router /v1/web/fetch using Ollama Cloud / Firecrawl / Jina Reader / Tavily Extract / Exa Contents. Use when the user wants to scrape a webpage, extract URL content, read article, or convert a URL to markdown.
9router-web-search
Web and X search via 9Router /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity / Xquik. Use when the user wants to search the web, find articles, or search public X posts.
9router-stt
Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.