confluence-property

confluence-property is a skill for Claude Code from ulises-jeremias/agent-toolkit. It costs 34 tokens per session (2,574 once invoked), scanned A, original, MIT.

A tool for storing custom key-value metadata on Confluence pages and blog posts. This metadata is structured information, such as a review status or approval date, attached to content.

In plain words
What is it for?
Use it to read, set, and delete custom properties for approvals, workflow tracking, external integrations, or other structured data.
Why use it?
It lets integrations and workflows store information that does not belong in the visible page text. The stored values can track process state or configuration.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agent-toolkit-complete plugin — 106 skills shipped together

Good fit Use it to read, set, and delete custom properties for approvals, workflow tracking, external integrations, or other structured data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ulises-jeremias/agent-toolkit/confluence-property
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 ulises-jeremias/agent-toolkit --skill confluence-property
Clone the repo
git clone --depth 1 https://github.com/ulises-jeremias/agent-toolkit

Made for: Claude Code.

Or install agent-toolkit-complete, the plugin that ships this one along with the rest of its 106 skills.

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-property

README.md
[![agentmods](https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/confluence-property/github.svg)](https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/confluence-property)
Your own site
<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/confluence-property"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/confluence-property/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 confluence-property

Your own site · 80×15
<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/confluence-property"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/confluence-property.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,574 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 211
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Excessive Agency · line 159
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 166
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00034 $0.02574
Opus 5.5 $0.00014 $0.01030
Sonnet 5.5 $0.00007 $0.00515
Haiku 4.5 $0.00003 $0.00257

Measured 20d ago against content hash d570dd7f5e69, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

confluence-property 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 20d 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.

plugins/agent-toolkit-complete/.github/skills/confluence-property/SKILL.md · 384 lines

How it starts

The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Confluence Property Skill


⚠️ PRIMARY USE CASE

This skill manages custom metadata on pages. Use for:

  • Storing custom key-value data on pages
  • Tracking workflow state (review status, approval)
  • Integration metadata for external systems
  • Structured data for automation

When to Use / When NOT to Use

Use This Skill Use Instead
Get/set custom metadata -
Store structured data -
Edit page content confluence-page
Add labels/tags confluence-label
Set permissions confluence-permission

Risk Levels

Operation Risk Notes
Get properties - Read-only
Set property - Can be overwritten
Delete property ⚠️ Data loss

Overview

Manages content properties on Confluence pages. Content properties are custom metadata stored as key-value pairs attached to a page. They are useful for storing application-specific data, configuration, or custom fields.

Use Cases:

  • Store custom metadata on pages (e.g., review status, approval date)
  • Implement custom workflows with property-based state tracking
  • Store configuration data for external integrations
  • Tag content with structured data for automated processing

CLI Commands

All commands use the confluence-as binary. The global -o/--output flag placed before the subcommand (e.g. confluence-as -o json property get 12345) sets the default output format for all subcommands; an explicit subcommand-level --output wins.

confluence-as property get

Retrieve content properties from a page.

Usage:

# Get all properties on a page
confluence-as property get 12345

# Get specific property by key
confluence-as property get 12345 --key my-property

# Get with expanded version info
confluence-as property get 12345 --expand version

# Output as JSON
confluence-as property get 12345 --output json

Options:

  • page_id - Page ID (required)
  • --key, -k - Specific property key to retrieve
  • --expand - Comma-separated fields to expand (e.g., version)
  • --output, -o - Output format: text or json

Read the full file on GitHub · 384 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. 20d ago Changed d570dd7f5e69
  2. 2mo ago First seen · 384 lines · 34 tokens per session scan A 6842ac5cdeac

Subscribe to this mod's changes

confluence-property is a skill published in the GitHub repository ulises-jeremias/agent-toolkit (19 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 2,574 once invoked, about $0.0001 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 2026-09-04.

Related

confluence-property compared with skills from other repositories

confluence-property next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
confluence-propertyulises-jeremias/agent-toolkitSkill19todayMITA34Claude Code
collectionluna-prompts/skillnoteSkill684d agoMITA39Codex
audit-accomplishmentspaultyng/skill-issueSkill820d agoMITA78Claude Code
start-daypaultyng/skill-issueSkill820d agoMITA69Claude Code, Codex
tracking-timeAstravueOrg/astravue-mcp-serverSkill122mo agoApache-2.0A53Claude Code
microsoft-outlookAceDataCloud/SkillsSkill17todaynoneA68Claude Code
google-calendarAceDataCloud/SkillsSkill17todaynoneA61Claude Code