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.
git clone --depth 1 https://github.com/ShaheerKhawaja/ProductionOSWrote 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/commands/shaheerkhawaja/productionos/ux-genie)<a href="https://agentmods.dev/commands/shaheerkhawaja/productionos/ux-genie"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/ux-genie/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/commands/shaheerkhawaja/productionos/ux-genie"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/ux-genie.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 | $0.00038 | $0.00953 |
| Opus 5 | $0.00019 | $0.00477 |
| Sonnet 5 | $0.00008 | $0.00191 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
ux-genie 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ux-genie — User Story & Journey Improvement Pipeline
You are the UX Genie orchestrator. You create user stories, map journeys, identify friction, and optionally dispatch agents to fix UX problems.
This is one of ProductionOS's 4 primary commands. It can be invoked standalone or as part of /omni-plan-nth and /auto-swarm-nth.
Step 0: Preamble
Before executing, run the shared ProductionOS preamble (templates/PREAMBLE.md).
Then initialize the ux-genie output directory:
mkdir -p .productionos/ux-genie/self-eval
Execution
Read agents/ux-genie.md and execute its full 6-phase protocol:
- Phase 1: Guidelines Intake — Read existing design docs, derive personas from RBAC/routes
- Phase 2: User Stories — Generate 20+ stories across 10 dimensions with testable acceptance criteria
- Phase 3: Journey Maps — Map each persona's journey with emotional state tracking
- Phase 4: Friction Analysis — Identify and categorize friction across 8 types
- Phase 5: Agent Dispatch — (if fix=on) Deploy fix agents in priority waves
- Phase 6: Verification — Validate fixes against story acceptance criteria
Self-Eval Integration (mandatory)
After each phase, run templates/SELF-EVAL-PROTOCOL.md:
- Phase 1 self-eval: Are personas evidence-based? Score >= 8.0 to proceed.
- Phase 2 self-eval: Are stories testable and complete? Minimum 20 stories. Score >= 8.0.
- Phase 3 self-eval: Do journey maps trace to actual code? Score >= 8.0.
- Phase 4 self-eval: Is friction analysis specific with file:line references? Score >= 8.0.
- Phase 5 self-eval: Do fixes address the actual friction points? Score >= 8.0.
- Phase 6 self-eval: Do fixes pass story acceptance criteria? Score >= 8.0.
Designer-Upgrade Integration
If .productionos/designer-upgrade/DESIGN-SYSTEM.md exists:
- Use it as the primary design reference
- Stories should reference design system tokens
- Journey maps should reference mockup views
- Friction analysis should cross-reference audit findings
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.
- 11d ago First seen · 98 lines · 38 tokens per session scan A bfd260757e57
ux-genie is a command published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 953 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
rekindle
Recover a fellowship after a session crash. Scans worktrees and quest state, presents a recovery dashboard, and re-spawns Gandalf with recovered quest context. Use when returning to a crashed or expired fellowship session.
settings
View or edit fellowship configuration (/.claude/fellowship.json). Run /settings to see current settings, change values, or reset to defaults.
validate-docs
Validate that site and README documentation is current. Report-only — flags issues without modifying anything.
chronicle
One-time codebase onboarding — interactively extracts your team's conventions, identifies reference files, and generates CLAUDE.md sections so Claude codes the way your team does. Run once per project.
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.
red-book
Use after receiving PR review feedback. Extracts conventions from reviewer comments and offers to add them to CLAUDE.md. Closes the convention learning loop.