mk:confluence-page

mk:confluence-page is a skill for Claude Code from ngocsangyem/MeowKit. It costs 115 tokens per session (912 once invoked), scanned A, original, MIT.

A Confluence page management tool for creating, viewing, editing, deleting, copying, moving, and inspecting page hierarchies. Confluence is a shared workspace for team documentation and specifications.

In plain words
What is it for?
Use it to create or update pages, read page content, inspect children or ancestors, copy pages, move them between spaces, or delete them.
Why use it?
It gathers common single-page operations in one place and helps preserve the page structure around a document. It is intended for individual pages rather than large batches or deep specification analysis.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: agent in frontmatter; reads .claude/ paths.

Good fit Use it to create or update pages, read page content, inspect children or ancestors, copy pages, move them between spaces, or delete them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ngocsangyem/meowkit/confluence-page
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 ngocsangyem/MeowKit --skill confluence-page
Clone the repo
git clone --depth 1 https://github.com/ngocsangyem/MeowKit

Made for: Claude Code.

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 mk:confluence-page

README.md
[![agentmods](https://agentmods.dev/badge/skills/ngocsangyem/meowkit/confluence-page/github.svg)](https://agentmods.dev/skills/ngocsangyem/meowkit/confluence-page)
Your own site
<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/confluence-page"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/confluence-page/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 mk:confluence-page

Your own site · 80×15
<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/confluence-page"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/confluence-page.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 912 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 $0.00115 $0.00912
Opus 5 $0.00057 $0.00456
Sonnet 5 $0.00023 $0.00182
Haiku 4.5 $0.00012 $0.00091

Measured 6d ago against content hash 194b480c8297, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mk:confluence-page 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 6d 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.

.claude/skills/confluence-page/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mk:confluence-page

Forks to the confluence-page agent (system prompt at .claude/agents/confluence-page.md). The skill body is the task brief — the host runtime injects this content into the forked agent.

Triggers

  • "create a page in SPACE titled '...'"
  • "show me / get / view page 12345"
  • "update title / body of page 12345"
  • "delete page 12345"
  • "list children / ancestors / descendants of page 12345"
  • "copy / move page 12345 to SPACE"

Examples

  • Quick create: "create a page in ENG titled 'Q3 Roadmap' with body from /tmp/draft.md"
  • Templated create: "create an RFC page in ENG from the rfc template"
  • Read with projection: "show me page 12345 in storage format"
  • Update: "set title to 'Q3 Roadmap (final)' on page 12345"
  • Hierarchy: "list children of page 12345 with depth 2"

See also

  • Agent: ../../agents/confluence-page.md
  • Shared: ../confluence/references/{install-and-auth,cli-idioms,safety-framework}.md
  • Domain refs:
    • references/page-templates.md — RFC / Runbook / Decision Record skeletons
    • references/field-formats.md — storage / view / export_view / ADF distinctions
    • references/version-restore-guide.md — version operations + restore semantics
  • Peer leaves: mk:confluence-search (CQL search + space list), mk:confluence-collaborate (comments / attachments / labels), mk:confluence-bulk (10+ pages), mk:confluence-spec-analyst (spec analysis)

Gotchas

  • Wrapper output is JSON only after the stdout filter runs. Do not parse raw confluence-as output — always go through the wrapper. [from research]
  • POST is in confluence-as retry allowed_methods. Create ops on flaky networks may produce duplicate pages. Before retrying a failed page create, list pages with the same title in the target space first. [from research]
  • ADF round-trip is lossy on panel, expand, mention, emoji, media, decision, task-list nodes. Re-saving a page with these macros via update may flatten them. See references/field-formats.md Round-Trip Caveats. [from research]
  • XHTML parsing in confluence-as is regex-based. Malformed or deeply nested storage format may fail silently. Prefer markdown via --content for fresh page bodies. [from research]
  • version restore creates a NEW version on top of head — it is not in-place rollback. See references/version-restore-guide.md. [from research]
  • Grow this list as new edge cases surface.

Read the full file on GitHub · 65 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. 6d ago First seen · 65 lines · 115 tokens per session scan A 194b480c8297

Subscribe to this mod's changes

mk:confluence-page is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 912 once invoked, about $0.0006 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 2026-09-03.