What is publish-and-workflow?

A controlled workflow for publishing, unpublishing, approving, declining, or deleting content and pages in Agility CMS, a system for managing website content. It identifies the exact workspace, language, and item before making changes.

Use it to make selected content live, take it offline without deleting it, send it through approval, approve or decline it, or remove it after the exact item is confirmed.

It reduces the risk of changing the wrong content or accidentally making something public. It also separates saving a draft from publishing it to the live website.

publish-and-workflow — Skill for Claude Code by agility/mcp-server

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 publish-and-workflow

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/agility/mcp-server/publish-and-workflow/github.svg)](https://agentmods.dev/skills/agility/mcp-server/publish-and-workflow)

Your own site

<a href="https://agentmods.dev/skills/agility/mcp-server/publish-and-workflow"><img src="https://agentmods.dev/badge/skills/agility/mcp-server/publish-and-workflow/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/agility/mcp-server/publish-and-workflow"><img src="https://agentmods.dev/badge/skills/agility/mcp-server/publish-and-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 746 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.

Model	Per session	Once invoked
Fable 5.1	$0.00054	$0.00746
Opus 5.5	$0.00022	$0.00298
Sonnet 5.5	$0.00011	$0.00149
Haiku 4.5	$0.00005	$0.00075

Measured 2d ago against content hash 7da0049a6d2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

publish-and-workflow 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/publish-and-workflow/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Publish, approve, unpublish and delete

These actions change what visitors see on the live site, or remove content. Run them only when the user asks, for content they have clearly identified.

Before acting

Identify exactly what to act on: instance, locale, and the content IDs or page IDs. If the request could match more than one item or page ("publish the new post"), look them up and ask the user to confirm which.
State what will happen in one line, for example: "Publishing item 412 'Spring launch' in en-us will make it live."
A request to save, draft or edit is not a request to publish. Never publish as a follow-on step the user did not ask for.

Which tool

User wants to	Content items	Pages
Make it live	`publish_content`	`publish_page`
Take it offline (keeps it in the CMS)	`unpublish_content`	`unpublish_page`
Submit, approve or decline in the approval workflow	`manage_content_workflow`	`manage_page_workflow`
Remove it	`delete_content_item`	`delete_page`

Prefer unpublishing over deleting when the user only wants something off the live site. For a delete, confirm the exact item or page with the user first and say that it removes the item.

Pages and their content

A page's modules (the components placed in its zones) are content items of their own. Publishing a page does not show that its modules' content is live. After publish_page, call get_page to list the module content IDs, then call get_content_item for each one and check its state. If any module's content is not published, tell the user which ones and offer to publish them with publish_content.

Large batches and timeouts

Publish or unpublish at most 16 IDs per call. Larger batches tend to time out, even though the tools accept up to 50.
A call that times out may still complete minutes later. Before retrying, read the items' state and retry only the ones that did not change.
After deleting a component's content item, publish its page again. Until then the live page still lists the deleted ID, which can break the site.

Read the full file on GitHub · 67 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.

2d ago First seen · 67 lines · 54 tokens per session scan A 7da0049a6d2b

Subscribe to this mod's changes

publish-and-workflow is a skill published in the GitHub repository agility/mcp-server (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 54 tokens to every session and 746 once invoked, about $0.0002 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.

Writing and docs

publish-and-workflow next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
publish-and-workflowagility/mcp-server	Skill	0	2d ago	Apache-2.0	A	54	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