edit-content

edit-content is a skill for Claude Code from agility/mcp-server. It costs 63 tokens per session (1,094 once invoked), scanned A, original, Apache-2.0.

A set of procedures for finding, creating, updating, and translating content in Agility CMS, a system for managing website content separately from the website code. It covers content fields, locales, drafts, links, images, and related items.

In plain words
What is it for?
It is for managing blog posts, articles, products, authors, and other CMS records, including creating items, changing fields, adding related content, and copying content between locales.
Why use it?
It helps prevent edits from going to the wrong language or content type and avoids saving data with guessed field names. It also verifies saved drafts and provides their editing links.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agility-cms plugin — 9 skills, 2 MCP servers shipped together

Good fit It is for managing blog posts, articles, products, authors, and other CMS records, including creating items, changing fields, adding related content, and copying content between locales.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agility/mcp-server/edit-content
Install

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.

Any agent
npx skills add agility/mcp-server --skill edit-content
Clone the repo
git clone --depth 1 https://github.com/agility/mcp-server

Made for: Claude Code.

Or install agility-cms, the plugin that ships this one along with the rest of its 9 skills, 2 MCP servers.

Wrote 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.

agentmods badge for edit-content

README.md
[![agentmods](https://agentmods.dev/badge/skills/agility/mcp-server/edit-content/github.svg)](https://agentmods.dev/skills/agility/mcp-server/edit-content)
Your own site
<a href="https://agentmods.dev/skills/agility/mcp-server/edit-content"><img src="https://agentmods.dev/badge/skills/agility/mcp-server/edit-content/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.

agentmods 80×15 button for edit-content

Your own site · 80×15
<a href="https://agentmods.dev/skills/agility/mcp-server/edit-content"><img src="https://agentmods.dev/badge/skills/agility/mcp-server/edit-content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,094 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.01094
Opus 5.5 $0.00025 $0.00438
Sonnet 5.5 $0.00013 $0.00219
Haiku 4.5 $0.00006 $0.00109

Measured 2d ago against content hash ad087dc47e72, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

edit-content 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.

plugins/agility-cms/skills/edit-content/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create and edit content in Agility CMS

Find the target

  • Confirm the instance and locale. Call get_locales if the locale has not been settled in this conversation. Content is per locale: saving to the wrong locale creates a separate item.
  • To find an item by text, title or ID, call search_instance. If search is not available for the instance, call get_containers and then get_content_items for the right container. Do not retry search repeatedly.
  • Before writing, call get_content_model_details for the container's model. Use the real field names, types and required fields. Ask the user for required values you do not have; do not invent them.

Create a new item

  1. Call save_content_items with contentID: -1, the container's referenceName, the locale, and the fields.
  2. Read the result. It gives the new contentID and an editUrl for each item.
  3. Call get_content_item with that contentID to confirm the saved values. A brand-new draft can be missing from get_content_items lists for a short time; reading it by ID is reliable.
  4. Tell the user the item is saved as a draft (not published) and give them the actual editUrl from the result.

Update an existing item

  1. Call get_content_item first. Note every field value and properties.versionID.
  2. Call save_content_items with the item's contentID, all of its fields (changed and unchanged), and properties.versionID set to the current version. Fields you leave out are wiped.
  3. Read the item back with get_content_item and confirm that only the intended fields changed.

If you no longer know which item to update, ask. Never guess a content ID.

Field formats

  • Links: {href, text, target}. Links inside the site use the ~/ prefix, for example ~/about-us.
  • Linked content (dropdowns and lists that point at other items): use the exact companion field names shown by get_content_model_details, and real content IDs read from the linked container.
  • Images and attachments: the field value is {url, label}.
    • To use an asset already in Agility, call list_media to find it and use its URL.
    • To add a new file the user has provided, call initialize_media_upload, POST the file to the returned uploadUrl within 5 minutes, and use the asset URL that the upload returns.
    • When updating an item, keep the existing URL for attachments that are not changing.
  • SEO and GEO fields only apply to items in a dynamic page list (a container whose items each generate a page). Leave them out for ordinary containers.
  • Release and pull dates: send releaseDate: null and pullDate: null unless the user is deliberately scheduling. A pull date in the past hides the item from the live site as soon as it is published. Dates are read as US Eastern time, so a date that looks a few hours ahead can already be past. Never copy dates from another item.
  • Workflow state cannot be set by saving. Every save lands in the instance's default state, usually Staging. Publishing is a separate step; see the publish-and-workflow skill.

Read the full file on GitHub · 95 lines

Changes

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.

  1. 2d ago First seen · 95 lines · 63 tokens per session scan A ad087dc47e72

Subscribe to this mod's changes

edit-content is a skill published in the GitHub repository agility/mcp-server (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,094 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.

Related

edit-content compared with skills from other repositories

edit-content next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
edit-contentagility/mcp-serverSkill02d agoApache-2.0A63Claude Code
intl-expansionalirezarezvani/claude-skillsSkill29k3d agoMITA27Claude Code
azure-ai-translation-text-pymicrosoft/skillsSkill3.2kyesterdayMITA60Claude Code
chinese-documentationjnMetaCode/superpowers-zhSkill8.5k12d agoMITA62Claude Code
hardenfengshao1227/ccg-workflowSkill6.0k6d agoMITA62Claude Code
edit-sitemicrosoft/power-platform-skillsSkill1.1kyesterdayMITA104Claude Code
asc-subscription-localizationrorkai/app-store-connect-cli-skillsSkill1.1kyesterdayMITA60Claude Code