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-bulkgit 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-bulk)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/confluence-bulk"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/confluence-bulk/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-bulk"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/confluence-bulk.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 | $0.00099 | $0.00749 |
| Opus 5.5 | $0.00040 | $0.00300 |
| Sonnet 5.5 | $0.00020 | $0.00150 |
| Haiku 4.5 | $0.00010 | $0.00075 |
Grade A, and why
mk:confluence-bulk 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 2mo 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-bulk
Forks to the confluence-bulk agent. The agent enforces a hard 3-step ceremony at runtime — dry-run → confirm → execute.
Dry-Run Workflow (MANDATORY)
Step 1: invocation + --dry-run
Step 2: agent shows would_* JSON keys + impacted-count + first 5 affected page titles
Step 3: explicit user "yes" + typed confirmation token (e.g. "DELETE 47 PAGES")
→ re-invoke without --dry-run
Skipping Step 1 is a hard violation. The agent will refuse if asked to skip.
Triggers
- "bulk update N pages"
- "mass label"
- "delete every page matching CQL"
- "bulk-move pages from SPACE-A to SPACE-B"
- "bulk-label every page in space ENG with 'archive'"
See also
- Agent:
../../agents/confluence-bulk.md - Shared:
../confluence/references/{install-and-auth,cli-idioms,safety-framework}.md(Tier 4 enforcement lives in safety-framework.md) - Domain refs:
references/safety-checklist.md— pre-flight checklist for any bulk operationreferences/dry-run-protocol.md— the 3-step ceremony in detail with example transcripts
- Peer leaves:
mk:confluence-search(CQL author + read-side overlap; same sanitizer),mk:confluence-page(single-page ops),mk:confluence-collaborate(comments / attachments at single-page scope)
Gotchas
- Default
--max-pagescap is 100. Higher values require explicit override + extra confirmation.confluence-asmay impose its own server-side limit (~200 typical). bulk deleteis soft-delete to trash — restore requires going through the Confluence UI manually. There is no--restore-from-trashop verified in v1.- Bulk ops are NOT transactional. Partial-failure (rate limit / per-page permission error) leaves the partial-progress count visible; remediation is re-run with
id NOT IN (<completed>). bulk restoreis intentionally absent from v1 — confluence-as does not expose it as a single subcommand. v2 may add it via per-page orchestration.- 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.
- 2mo ago First seen · 65 lines · 99 tokens per session scan A 2117458a2c72
mk:confluence-bulk is a skill published in the GitHub repository ngocsangyem/MeowKit (15 stars, last pushed 6d ago), licensed MIT. It adds 99 tokens to every session and 749 once invoked, about $0.0004 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 2026-09-03.
mk:confluence-bulk compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mk:confluence-bulkngocsangyem/MeowKit | Skill | 15 | 6d ago | MIT | A | 99 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| gogopenclaw/openclaw | Skill | 394k | today | MIT | A | 20 | Claude Code, Codex |
| boxNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 14 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 33 | Claude Code, Codex |
| material-organizerOrkas-AI/Orkas | Skill | 9.1k | today | MIT | A | 3 | Claude Code, Codex |
| recipe-save-email-attachmentsgoogleworkspace/cli | Skill | 32k | 4d ago | Apache-2.0 | A | 20 | Claude Code, Codex |