publish-to-confluence

publish-to-confluence is a skill for Claude Code, Codex from Future-CX/AI-Architecture-Toolkit. It costs 55 tokens per session (1,967 once invoked), scanned A, original, MIT.

A tool that publishes Markdown or HTML documents as pages in Confluence, a team workspace for shared documentation. It can also handle local images referenced by the document.

In plain words
What is it for?
Use it to publish, update, sync, or push local documentation and generated toolkit artifacts to a Confluence space. Supported source files include Markdown and HTML.
Why use it?
It removes the manual copying and formatting needed to move architecture notes, designs, decisions, or other documents into Confluence. It uses configured Confluence credentials and space settings to send the content through the Confluence API.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to publish, update, sync, or push local documentation and generated toolkit artifacts to a Confluence space. Supported source files include Markdown and HTML.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/future-cx/ai-architecture-toolkit/publish-to-confluence
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 Future-CX/AI-Architecture-Toolkit --skill publish-to-confluence
Clone the repo
git clone --depth 1 https://github.com/Future-CX/AI-Architecture-Toolkit

Made for: Claude Code, Codex.

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 publish-to-confluence

README.md
[![agentmods](https://agentmods.dev/badge/skills/future-cx/ai-architecture-toolkit/publish-to-confluence/github.svg)](https://agentmods.dev/skills/future-cx/ai-architecture-toolkit/publish-to-confluence)
Your own site
<a href="https://agentmods.dev/skills/future-cx/ai-architecture-toolkit/publish-to-confluence"><img src="https://agentmods.dev/badge/skills/future-cx/ai-architecture-toolkit/publish-to-confluence/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 publish-to-confluence

Your own site · 80×15
<a href="https://agentmods.dev/skills/future-cx/ai-architecture-toolkit/publish-to-confluence"><img src="https://agentmods.dev/badge/skills/future-cx/ai-architecture-toolkit/publish-to-confluence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,967 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 $0.00055 $0.01967
Opus 5 $0.00028 $0.00983
Sonnet 5 $0.00011 $0.00393
Haiku 4.5 $0.00006 $0.00197

Measured 10d ago against content hash 33ce78731fa7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

publish-to-confluence 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/publish-to-confluence.py, scripts/test_publish_to_confluence.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/publish-to-confluence/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Publish To Confluence

Quick Start

Publish a markdown or HTML file to Confluence using the helper script:

python3 skills/publish-to-confluence/scripts/publish-to-confluence.py path/to/document.md \
  --space-key ARCH

When this toolkit is used as a submodule in a private lab repository, run the script from the private lab root:

python3 toolkit/skills/publish-to-confluence/scripts/publish-to-confluence.py outputs/design.md

Inputs

  • CONFLUENCE_BASE_URL, such as https://example.atlassian.net/wiki.
  • CONFLUENCE_EMAIL and CONFLUENCE_API_TOKEN for Confluence Cloud basic authentication.
  • CONFLUENCE_SPACE_KEY for the default Confluence publishing space.
  • A source .md, .html, or .htm file.
  • Any local image files referenced by markdown image syntax, such as ![Diagram](diagram.svg).
  • A page title in the first line of the source document.
  • Optional overview page title. Defaults to Overview.

Never commit API tokens, credentials, private Confluence URLs, customer names, or real company content to this public toolkit repository.

Credential Storage

The helper loads Confluence settings from .env in the current working directory. When values are missing, it asks the user for them and stores the missing values in that .env file with owner-only file permissions.

When this toolkit is mounted as toolkit/ in a private lab repo, always run the command from the private lab root so credentials are stored in <private-lab-root>/.env, not in the public toolkit submodule.

The expected .env keys are:

CONFLUENCE_BASE_URL="https://example.atlassian.net/wiki"
CONFLUENCE_EMAIL="[email protected]"
CONFLUENCE_API_TOKEN="..."
CONFLUENCE_SPACE_KEY="ARCH"

Use --env-file <path> only when the private repo keeps local secrets somewhere other than <private-lab-root>/.env.

Use --space-key <key> when publishing to a different space for one run. If .env does not yet contain CONFLUENCE_SPACE_KEY, the script stores the provided --space-key value there.

Read the full file on GitHub · 103 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 103 lines · 55 tokens per session scan A 33ce78731fa7

Subscribe to this mod's changes

publish-to-confluence is a skill published in the GitHub repository Future-CX/AI-Architecture-Toolkit (5 stars, last pushed 7d ago), licensed MIT. It adds 55 tokens to every session and 1,967 once invoked, about $0.0003 per session on Opus 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 2026-08-31.