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.
npx skills add ngocsangyem/MeowKit --skill confluence-collaborategit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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.
[](https://agentmods.dev/skills/ngocsangyem/meowkit/confluence-collaborate)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/confluence-collaborate"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/confluence-collaborate/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.
<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/confluence-collaborate"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/confluence-collaborate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00097 | $0.00746 |
| Opus 5 | $0.00048 | $0.00373 |
| Sonnet 5 | $0.00019 | $0.00149 |
| Haiku 4.5 | $0.00010 | $0.00075 |
Grade A, and why
mk:confluence-collaborate 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 5d 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.
What it actually says
mk:confluence-collaborate
Forks to the confluence-collaborate agent. The agent prefers footer comments over inline; asks before posting an inline comment.
Triggers
- "add comment to page 12345: ''"
- "list comments on page 12345"
- "upload screenshot.png to page 12345"
- "label page 12345 as 'urgent'"
- "remove label 'draft' from page 12345"
- "watch page 12345" / "stop watching page 12345"
- "list watchers of page 12345"
Examples
- Footer comment: "add comment to 12345: 'awaiting backend fix'"
- Attachment upload: "attach /tmp/repro.mp4 to page 12345"
- Label add: "label 12345 as 'rfc'"
- Watcher list: "who watches page 12345?"
See also
- Agent:
../../agents/confluence-collaborate.md - Shared:
../confluence/references/{install-and-auth,cli-idioms,safety-framework}.md - Domain refs:
references/comment-formats.md— inline vs footer, markdown vs storage formatreferences/attachment-conventions.md— file size limits, allowed types, download paths
- Peer leaves:
mk:confluence-page(page CRUD; create-with-attachment),mk:confluence-bulk(bulk-label across 10+ pages),mk:confluence-spec-analyst(downloads attachments for image analysis)
Gotchas
validate_file_pathinconfluence-asrejects..traversal but delegates to opaqueassistant-skills-lib. Don't trust delegation alone — the agent independently validates upload paths at the agent boundary too. [from research]- Confluence Cloud comments do NOT have a strict internal/public flag like Jira Service Management. Inline vs footer is the closest semantic boundary — agent prefers footer. [from jira-collaborate parallel pattern]
- Inline comment requires an anchor selection. If the selection text doesn't match unique content on the page, the comment fails with a 400-class error.
- Bulk-label across 10+ pages goes through
mk:confluence-bulk, NOT this skill. Single-page label add/remove only here. - Grow this list as new edge cases surface.
What ships with it
2 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.
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.
- 5d ago First seen · 63 lines · 97 tokens per session scan A 75a64e03153d
mk:confluence-collaborate is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 746 once invoked, about $0.0005 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.
Other skills, from other repositories
gws-drive
Google Drive: Manage files, folders, and shared drives.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.
recipe-share-doc-and-notify
Share a Google Docs document with edit access and email collaborators the link.
recipe-bulk-download-folder
List and download all files from a Google Drive folder.
recipe-save-email-to-doc
Save a Gmail message body into a Google Doc for archival or reference.
book-pdf
A document-to-book publishing workflow that turns Markdown—a plain-text writing format—into book-style PDF and EPUB files. It includes book pages such as a cover, copyright page, numbered contents, chapter breaks, running headers, and page numbers.