cf-publish

cf-publish is a skill for Claude Code from indranilbanerjee/contentforge. It costs 29 tokens per session (4,746 once invoked), scanned A, original, MIT.

A publishing step for ContentForge that sends approved content to Webflow or WordPress, two systems for managing and publishing websites.

In plain words
What is it for?
Publishing finished content as a draft, scheduled post, or live page, checking the result afterward, or exporting HTML for manual upload.
Why use it?
It removes manual copy-pasting and adds a preview and confirmation step before content is drafted, scheduled, or published.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

Part of the contentforge plugin — 22 skills, 9 commands, 13 agents shipped together

Good fit Publishing finished content as a draft, scheduled post, or live page, checking the result afterward, or exporting HTML for manual upload.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/indranilbanerjee/contentforge/cf-publish
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 indranilbanerjee/contentforge --skill cf-publish
Clone the repo
git clone --depth 1 https://github.com/indranilbanerjee/contentforge

Made for: Claude Code.

Or install contentforge, the plugin that ships this one along with the rest of its 22 skills, 9 commands, 13 agents.

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 cf-publish

README.md
[![agentmods](https://agentmods.dev/badge/skills/indranilbanerjee/contentforge/cf-publish/github.svg)](https://agentmods.dev/skills/indranilbanerjee/contentforge/cf-publish)
Your own site
<a href="https://agentmods.dev/skills/indranilbanerjee/contentforge/cf-publish"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/contentforge/cf-publish/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 cf-publish

Your own site · 80×15
<a href="https://agentmods.dev/skills/indranilbanerjee/contentforge/cf-publish"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/contentforge/cf-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,746 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00029 $0.04746
Opus 5.5 $0.00012 $0.01898
Sonnet 5.5 $0.00006 $0.00949
Haiku 4.5 $0.00003 $0.00475

Measured 18d ago against content hash 66aaa7038595, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cf-publish 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 18d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

skills/cf-publish/SKILL.md · 511 lines

How it starts

The opening of the file, as written. The whole thing — 511 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Publish Content — ContentForge CMS Publishing

Push publication-ready content from the ContentForge pipeline directly to your CMS (Webflow or WordPress) via MCP connectors. Preview before publishing, verify post-publish, and fall back to HTML export when no connector is available.

Execution gate

Nothing is sent to a CMS until the full publish preview (Step 4) has been shown and the user has typed yes. edit goes back to the draft; any other reply, including silence, cancels. A request such as "push this live" starts this flow; it never skips the preview.

When to Use

Use /contentforge:cf-publish when:

  • You have a finished, reviewed content piece (Phase 8 complete, score >=7.0)
  • You want to publish directly to Webflow or WordPress without copy-pasting
  • You need to schedule content for a future publish date
  • You want post-publish verification (URL live, meta tags correct, images loaded)
  • You want an HTML export for manual upload when no CMS connector is configured

Do NOT use for:

  • Content still in pipeline (must be Phase 8 complete)
  • Content that did not reach APPROVED (anything below 7.0 — a 5.0-6.9 piece is review_required, not publishable)
  • Platforms other than Webflow/WordPress (use /contentforge:cf-social-adapt for social media)

What This Command Does

  1. Verify Connector -- Check if Webflow or WordPress MCP connector is active
  2. Load Content -- Pull finished content from Google Drive or local output
  3. Format for Platform -- Convert markdown/docx to platform-specific HTML/blocks
  4. Preview -- Show rendered preview with meta tags, slug, featured image
  5. AI Disclosure & Provenance -- EU AI Act Article 50 check (applicable from 2 Aug 2026)
  6. Publish/Schedule -- Push to CMS as draft, published, or scheduled
  7. Post-Publish Verification -- Confirm URL is live, meta tags are correct, content renders properly
  8. Fallback -- If no connector, generate standalone HTML file for manual upload

Read the full file on GitHub · 511 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. 18d ago Changed · +4 lines · -139 tokens per session 66aaa7038595
  2. 23d ago Changed · +1 lines 591ea96601a5
  3. 1mo ago First seen · 506 lines · 168 tokens per session scan A 8ecc4743537d

Subscribe to this mod's changes

cf-publish is a skill published in the GitHub repository indranilbanerjee/contentforge (32 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 4,746 once invoked, about $0.0001 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 2026-08-30.