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 agility/mcp-server --skill content-modelinggit clone --depth 1 https://github.com/agility/mcp-serverWrote 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/agility/mcp-server/content-modeling)<a href="https://agentmods.dev/skills/agility/mcp-server/content-modeling"><img src="https://agentmods.dev/badge/skills/agility/mcp-server/content-modeling/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/agility/mcp-server/content-modeling"><img src="https://agentmods.dev/badge/skills/agility/mcp-server/content-modeling.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00064 | $0.00904 |
| Opus 5.5 | $0.00026 | $0.00362 |
| Sonnet 5.5 | $0.00013 | $0.00181 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
content-modeling 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content models, components and containers
How Agility structures content
- A content model defines the fields of a type of content, such as Blog Post.
- A container is a list of items that use one content model, such as BlogPosts. Content items are saved into containers. One model can back several containers.
- A component model defines a module that editors place in a page zone.
- A page model defines a page template and its zones.
To explain an instance, call get_content_models, get_component_models,
get_page_models and get_containers, then get_content_model_details or
get_component_model_details for the ones that matter. Describe how they connect:
which containers use which model, and which fields link to other content.
Changing a model: read, modify, save the whole thing
- Read the model with
get_content_model_details(orget_component_model_details). - Change only what the user asked for.
- Save the complete model: every field, with every setting it had. A save replaces each field's settings, so a setting you leave out is removed.
- Read the model again and confirm the change and that the other fields are unchanged.
Use save_component_model for components and save_content_model for content
models. They take the same shape, but are not interchangeable: saving a component
through save_content_model converts it and orphans its content.
Changing or removing a field on a model that already has content affects every item using it. Say this before saving, and say which containers use the model.
Creating new models and containers
- Check the existing models (
get_content_models,get_component_models) and containers (get_containers) first. Reuse or extend before creating. - There is no tool to delete a model. A model created by mistake stays in the instance. Confirm the name, reference name and fields with the user before the first save.
- After creating a content model, create a container for it with
save_containerso editors can add items.
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 · 80 lines · 64 tokens per session scan A 23f59fea36c8
content-modeling is a skill published in the GitHub repository agility/mcp-server (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 64 tokens to every session and 904 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-06.
content-modeling compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| content-modelingagility/mcp-server | Skill | 0 | 2d ago | Apache-2.0 | A | 64 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |