agentmods.dev

mk:confluence-search

mk:confluence-search is a skill for Claude Code from ngocsangyem/MeowKit. It costs 94 tokens per session (813 once invoked), scanned A, original, MIT.

A Confluence search and export tool using Confluence Query Language, or CQL, which is a structured way to filter wiki content. It can search pages, list spaces, handle saved filters, and export results.

In plain words
What is it for?
Use it to find recently changed pages, search by space or title, build or validate CQL queries, list spaces, manage saved filters, or export results.
Why use it?
It makes it easier to find pages with precise conditions while safely handling search terms supplied by users. It also avoids using page-editing tools for read and search tasks.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: agent in frontmatter.

not rated 14repo 1mo ago A scan 94 tokens original MIT

Good fit Use it to find recently changed pages, search by space or title, build or validate CQL queries, list spaces, manage saved filters, or export results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ngocsangyem/meowkit/confluence-search
View source ↗ ngocsangyem/MeowKit docs.meowkit.dev
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-search
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-search

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/confluence-search"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/confluence-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 813 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 $0.00094 $0.00813
Opus 5 $0.00047 $0.00407
Sonnet 5 $0.00019 $0.00163
Haiku 4.5 $0.00009 $0.00081

Measured 5d ago against content hash 9698c22daa8c, 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-search 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.

.claude/skills/confluence-search/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forks to the confluence-search agent. CQL is positional on search (and on validate / build helpers); flags everywhere else. The agent enforces CQL sanitization for any user-derived term via ../confluence/scripts/cql-sanitize.sh.

Triggers

  • "search confluence for ..."
  • "find pages where space = ENG and title ~ 'roadmap'"
  • "build a cql for ..."
  • "export the search to /tmp/out.csv"
  • "list / get / favourite a saved filter"
  • "list spaces" / "get space ENG"

Examples

  • "find pages updated in the last 7 days in space ENG, top 20"
  • "validate this cql: space = ENG AND title ~ 'Q3'"
  • "list every space I can see"
  • "save a filter named 'My recent specs' with this cql: ..."

See also

  • Agent: ../../agents/confluence-search.md
  • Shared: ../confluence/references/{install-and-auth,cli-idioms,safety-framework}.md
  • Domain refs:
    • references/cql-patterns.md — canonical CQL templates (curated)
    • references/cql-reference.md — full CQL operator + function reference
    • references/search-examples.md — practical query examples per scenario
  • Peer leaves: mk:confluence-bulk (write-side bulk by CQL — same dry-run discipline), mk:confluence-spec-analyst (read-only deep analysis), mk:confluence-page (single-page CRUD)

Gotchas

  • confluence-as does NOT export _escape_cql_string — it lives as a private function in the search command module. The cql-sanitize.sh shared script is the only safety gate. Use it unconditionally for any user-derived CQL term. [from research]
  • The --quiet global flag is declared in confluence-as but unimplemented (never read in main). Don't rely on it; redirect stderr explicitly when needed. [from research]
  • Keychain entry name "confluence-assistant" collides with upstream Confluence-Assistant-Skills if both tools are installed. We never use keychain (env-only via wrapper) so we're not affected — but document the collision so users running both know. [from research]
  • Two-tier filesystem cache (SkillCache SQLite + ~/.confluence-skills/cache/) is opaque. Don't depend on cache state — confluence-as ops cache-clear is safe to invoke if behavior looks stale. [from research]
  • Grow this list as new edge cases surface.

Read the full file on GitHub · 62 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. 5d ago First seen · 62 lines · 94 tokens per session scan A 9698c22daa8c

Subscribe to this mod's changes

mk:confluence-search is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 813 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.

Claude CodeDocumentsResearchaiai-agentsautomationclaudeclaude-skillsconfluence-exportconfluence-filterconfluence-searchconfluence-space-listcqlcql-query
Related

Other skills, from other repositories

daily-report-generator

Automatically generate daily construction reports from field data, worker inputs, weather, and progress photos. Creates professional PDF reports.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 27 tokens

dgn-to-excel

Convert DGN files (v7-v8) to Excel databases. Extract elements, levels, and properties from infrastructure CAD files.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 32 tokens

dwg-to-excel

Convert AutoCAD DWG files (1983-2026) to Excel databases using DwgExporter CLI. Extract layers, blocks, attributes, and geometry data without Autodesk licenses.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 42 tokens

ifc-to-excel

Convert IFC files (2x3, 4x1, 4x3) to Excel databases using IfcExporter CLI. Extract BIM data, properties, and geometry without proprietary software.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 45 tokens

drawing-analyzer

Analyze construction drawings to extract dimensions, annotations, symbols, and metadata. Support quantity takeoff and design review automation.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 27 tokens

pdf-report-generator

Automatically generate PDF reports from construction data. Create formatted project reports with charts and tables.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 21 tokens