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 agents/jeremylongworth-source/agentskills/agents.creator-content-enginegit clone --depth 1 https://github.com/jeremylongworth-source/AgentSkillsWrote 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/agents/jeremylongworth-source/agentskills/agents.creator-content-engine)<a href="https://agentmods.dev/agents/jeremylongworth-source/agentskills/agents.creator-content-engine"><img src="https://agentmods.dev/badge/agents/jeremylongworth-source/agentskills/agents.creator-content-engine.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 | $0.00000 | $0.00481 |
| Opus 5 | $0.00000 | $0.00241 |
| Sonnet 5 | $0.00000 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
AGENTS.creator-content-engine 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 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.
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.
What it actually says
Use local skills as the primary routing layer for creator content engine work.
Use content-pillars when defining creator content strategy, audience promise,
recurring themes, and content lanes.
Use short-form-hooks for TikTok, Reels, Shorts, LinkedIn, X, and other
short-form opening lines, first beats, and retention-oriented hooks.
Use video-script for creator video scripts, shot outlines, voiceover,
talking points, b-roll, on-screen text, CTAs, and cutdown ideas.
Use ai-video-prompt-pack for AI-generated video prompt packs, scene timing,
prompt variants, negative prompts, safe areas, and platform/model constraints.
Use thumbnail-title-brief for YouTube and video title packs, thumbnail
creative briefs, title-thumbnail pairings, and test variants.
Use social-asset-production for profile images, banners, post images,
article covers, thumbnails, short-video covers, and crop-safe export checks.
Use caption-writer for social captions, CTAs, community prompts, sponsor
disclosure notes, hashtag notes, and caption variants.
Use content-calendar when building 7-day, 30-day, weekly, or campaign
publishing calendars.
Use longform-to-shorts when repurposing videos, podcasts, livestreams,
newsletters, blogs, or interviews into short-form assets.
Use newsletter-repurpose for newsletter versions, subject lines, creator
digests, email intros, and newsletter-to-social cutdowns.
Use podcast-outline for episode outlines, guest questions, sponsor slots,
talking points, and clip opportunities.
Use owned-social-profile-audit and brand-social-launch-pack for profile
positioning, bios, links, pinned/featured content, launch posts, social assets,
and coordinated owned-channel launch packages.
Use publishing-checklist for pre-publish QA, disclosure, rights, metadata,
accessibility, approval, and post-publish monitoring checks.
Use content-seo-strategy for search-oriented content strategy and
concise-technical-writing for tight scripts, calendars, briefs, and checklists.
Do not publish, schedule, send sponsor content, or make public claims without explicit approval. Verify current platform rules, disclosure requirements, and format specs when exact tactical guidance matters.
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 · 49 lines · 0 tokens per session scan A 4d2351768801
AGENTS.creator-content-engine is an agent published in the GitHub repository jeremylongworth-source/AgentSkills (1 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 481 tokens. 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 agents, from other repositories
github.awesome-copilot.agents
MCP server that suggests repository-specific AI agent skills.
dotnet.skills.plugins.dotnet-test.agents
MCP server that suggests repository-specific AI agent skills.
runceel.ai-dev-template..github.agents
MCP server that suggests repository-specific AI agent skills.
addyosmani.agent-skills.agents
MCP server that suggests repository-specific AI agent skills.
dotnet.skills.plugins.dotnet-diag.agents
MCP server that suggests repository-specific AI agent skills.
garrytan.gstack.agents
MCP server that suggests repository-specific AI agent skills.