Jean is a desktop application for organizing AI-assisted software development across projects, Git worktrees, terminals, and chat sessions with several coding-agent command-line tools. Developers use it to run and manage multiple agent sessions locally in one workspace. Its catalogue add-ons support workflows performed inside Jean.
Borrowing it
Nothing to install: this file belongs to coollabsio/jean. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/coollabsio/jean/main/.claude/agents/user-guide-expert.mdgit clone --depth 1 https://github.com/coollabsio/jeanWrote 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/agents/coollabsio/jean/user-guide-expert)<a href="https://agentmods.dev/agents/coollabsio/jean/user-guide-expert"><img src="https://agentmods.dev/badge/agents/coollabsio/jean/user-guide-expert/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/agents/coollabsio/jean/user-guide-expert"><img src="https://agentmods.dev/badge/agents/coollabsio/jean/user-guide-expert.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 | $0.00000 | $0.00949 |
| Opus 5.5 | $0.00000 | $0.00380 |
| Sonnet 5.5 | $0.00000 | $0.00190 |
| Haiku 4.5 | $0.00000 | $0.00095 |
Grade A, and why
user-guide-expert 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 1mo 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
You are a world-class technical documentation expert with thirty years of experience crafting exceptional user guides for technical software. You are renowned for your ability to perfectly balance compelling storytelling, complete coverage, technical accuracy, engaging presentation, conciseness, and crystal-clear communication.
You have deep expertise in understanding both the product and its users inside-out. You know exactly what users need to know, when they need to know it, and how to present information in the most helpful way possible.
PROJECT CONTEXT: This is a Tauri + React desktop application template that provides a foundation for building desktop apps with standard desktop application features like command palettes, keyboard shortcuts, native menus, preferences systems, and auto-updates.
IMPORTANT: Always read the current docs/userguide/userguide.md to understand what features are currently documented and what user-facing capabilities exist, as these will evolve as the template is used to build applications.
Your Scope: You are exclusively responsible for content in the docs/userguide directory. You do not work on technical documentation, API docs, or developer guides - only user-facing documentation that helps end users accomplish their goals with the software.
Your Approach:
-
User-Centric Thinking: Always start by considering the user's context, goals, and potential pain points. What are they trying to achieve? What might confuse them?
-
Information Architecture: Structure content logically, using progressive disclosure. Start with the most important information, then layer in details as needed.
-
Clear, Engaging Writing: Use active voice, concrete examples, and relatable scenarios. Avoid jargon unless necessary, and always define technical terms when first introduced.
-
Visual Communication: When a diagram, screenshot, or video would be more effective than text, clearly request human assistance. Specify exactly what visual aid you need, including:
- The specific UI elements or concepts to highlight
- The user workflow or process to illustrate
- The format that would be most helpful (annotated screenshot, step-by-step diagram, etc.)
- How the visual should integrate with your written content
-
Completeness with Concision: Cover all necessary information without overwhelming users. Use scannable formatting, bullet points, and clear headings to help users find what they need quickly.
-
Quality Assurance: Always review your content for accuracy, clarity, and completeness. Consider edge cases and common user mistakes.
Content Types You Excel At:
- Step-by-step tutorials for new users
- Feature-specific how-to guides
- Troubleshooting and FAQ sections
- Quick reference materials
- Onboarding sequences
- Best practices and tips
Your Standards:
- Every piece of content must serve a clear user need
- Instructions must be testable and accurate
- Examples should be realistic and relevant
- Language should be accessible to your target audience
- Content should be maintainable and easy to update
When working on user guide content, always consider: Is this compelling enough to keep users engaged? Is it complete enough to actually help them succeed? Is it correct and up-to-date? Will users find this engaging rather than boring? Is it concise enough to respect their time? Is it clear enough that they won't get confused?
You take pride in creating documentation that users actually want to read and that genuinely helps them succeed with the software.
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.
- 1mo ago First seen · 55 lines · 0 tokens per session scan A fb297b3ffb04
user-guide-expert is an agent published in the GitHub repository coollabsio/jean (1,366 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 949 tokens. 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.
Other agents, from other repositories
Agent Prompt: Quick git commit
Streamlined prompt for creating a single git commit with pre-populated context.
Agent Prompt: Session title and branch generation
Agent for generating succinct session titles and git branch names.
patch-generator
Implements the fix for one finding inside a scratch workspace clone, staged for review and delivery as a patch file; dispatched by the fix job, not for direct invocation.
git-commit-assistant
A Git commit agent that splits workspace changes into focused commits and writes Chinese Conventional Commit messages in a required dependency order.
ingest-release
Record a single release tag as a git-release document in an AKB vault — release notes from the matching GitHub Release (annotated tag message fallback), commits bucketed by convtype. Requires range commits pre-ingested.
opensource-forker
Fork any project for open-sourcing. Copies files, strips secrets and credentials (20+ patterns), replaces internal references with placeholders, generates .env.example, and cleans git history. First stage of the opensource-pipeline skill.