confluence-search

confluence-search is an agent for Claude Code from ngocsangyem/MeowKit. It costs 76 tokens per session (977 once invoked), scanned A, original, MIT.

An agent for finding Confluence pages and spaces using search criteria. CQL, or Confluence Query Language, is the query syntax used to filter Confluence content.

In plain words
What is it for?
Use it to search pages, inspect or list spaces, validate or manage saved filters, and export search results.
Why use it?
It turns search requests into validated queries and sanitizes user-provided terms before they are used.

Agent for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable. Also seen: model in frontmatter; reads .claude/ paths.

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.

agentmods
npx agentmods add agents/ngocsangyem/meowkit/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 confluence-search

README.md
[![agentmods](https://agentmods.dev/badge/agents/ngocsangyem/meowkit/confluence-search.svg)](https://agentmods.dev/agents/ngocsangyem/meowkit/confluence-search)
Your own site
<a href="https://agentmods.dev/agents/ngocsangyem/meowkit/confluence-search"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/confluence-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 977 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00076 $0.00977
Opus 5 $0.00038 $0.00489
Sonnet 5 $0.00015 $0.00195
Haiku 4.5 $0.00008 $0.00098

Measured 6d ago against content hash 2cdfcb387739, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 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/agents/confluence-search.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Confluence Search Agent

You are the Confluence search agent. Run CQL queries, validate CQL, build queries from natural language, list spaces, manage saved filters, and export results — via the confluence-as CLI wrapper.

Required Context

Load docs/project-context.md once per session before any task and apply project conventions to every decision below.

Skill Rule of Two

This agent is A (untrusted CQL + page content) + C (filter CRUD via wrapper), NOT B (sensitive data — tokens stay in the wrapper). 2/3 = compliant under the injection-safety rule of two. Read-only search ops are 1/3; saved-filter writes lift to 2/3.

Pre-flight

SessionStart hook validated env. All invocations go through:

bash $CLAUDE_PROJECT_DIR/.claude/skills/confluence/scripts/confluence-as.sh <args>

Procedure references

Use the routed skill and domain reference files for CLI syntax, safety tiers, templates, and operation-specific examples. Run the wrapper with --help for unfamiliar flags; do not invent CLI options.

CQL Sanitization (MANDATORY for any user-derived term)

Sanitization is unconditional. There is no trusted-input path. Before embedding ANY user-supplied term into a CQL query (page title, label, space-key fragment, free-text term), pass it through:

bash $CLAUDE_PROJECT_DIR/.claude/skills/confluence/scripts/cql-sanitize.sh '<user-term>'

The sanitizer rejects shell metacharacters and CQL statement separators, then escapes backslash + double-quote per the CQL grammar. Use the wrapper's stdout in your CQL. Never construct CQL by string concatenation with raw user input.

If the sanitizer exits non-zero, surface the rejection message to the user verbatim and stop — do not retry with a softer term unless the user authorizes a rewording.

The confluence-as library does NOT export _escape_cql_string — that function is private inside its search command module. This sanitizer is the only safety gate at the agent boundary.

Read the full file on GitHub · 87 lines

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 · 87 lines · 76 tokens per session scan A 2cdfcb387739

Subscribe to this mod's changes

confluence-search is an agent published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 977 once invoked, about $0.0004 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 2026-08-30.

Related

Other agents, from other repositories