Borrowing it
Nothing to install: this file belongs to Islanders-Treasure0969/claude-pilot. 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/Islanders-Treasure0969/claude-pilot/main/.claude/commands/ux-story-gen.mdgit clone --depth 1 https://github.com/Islanders-Treasure0969/claude-pilotWrote 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/islanders-treasure0969/claude-pilot/ux-story-gen)<a href="https://agentmods.dev/commands/islanders-treasure0969/claude-pilot/ux-story-gen"><img src="https://agentmods.dev/badge/commands/islanders-treasure0969/claude-pilot/ux-story-gen/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/islanders-treasure0969/claude-pilot/ux-story-gen"><img src="https://agentmods.dev/badge/commands/islanders-treasure0969/claude-pilot/ux-story-gen.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 | $0.00020 | $0.01182 |
| Opus 5 | $0.00010 | $0.00591 |
| Sonnet 5 | $0.00004 | $0.00236 |
| Haiku 4.5 | $0.00002 | $0.00118 |
Grade A, and why
ux-story-gen 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are generating UX improvement user stories for Claude Pilot itself. This command is a dog-fooding tool for Claude Pilot developers, not a feature shipped to end users. The output becomes the next PRD that the team implements.
Inputs (read these in order)
-
PRODUCT.md(required) — product vision, personas, pains, principles, pillars, anti-goals, and success signals. This is the source of truth. Do not propose anything that violates §4 (Principles) or §6 (Anti-goals). -
.local/prd/_feedback-log.md(optional, skip if missing) — history of phase reversions and rework reasons. Patterns here are strong hints for real pain. -
.local/claude_pilot/state/usage-analytics.json(optional, skip if missing) — feature usage counters. Unused features are candidates for discovery improvement or removal, not new feature piles. -
Existing
.local/prd/prd-*/stories.md(required scan) — read titles only, to avoid proposing stories that are already in flight or shipped. Do not duplicate. -
Memory:
memory/feedback_ux_vision.md(optional) — older UX intent notes from the maintainer. Treat as historical context, not current direction.PRODUCT.mdoverrides it on any conflict.
Process
Work in this order. Do not skip steps.
Step 1 — Ground yourself in PRODUCT.md
Re-read §2 (Persona), §3 (Pains), §4 (Principles), §5 (UX Pillars), and §6 (Anti-goals). Keep these in working memory while generating.
Step 2 — Gather signal
Read feedback log, usage analytics, and recent PRD titles if they exist. Build a short list of real pain signals. Note any feature that has 0 usage after being shipped — that's a signal too.
Step 3 — Generate candidate stories
Draft 5 to 8 candidate user stories. Each must satisfy all of the following:
- Traces to at least one numbered pain from §3 (cite the number)
- Belongs to exactly one UX pillar from §5 as primary
- Targets at least one persona from §2 (P1/P2/P3)
- Does not violate any anti-goal from §6
- Is not a duplicate of an existing PRD in
.local/prd/ - Has acceptance criteria that can be evaluated by a gate rule (checklist, keyword, or file_exists). Avoid vague criteria like "feels better".
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 · 124 lines · 20 tokens per session scan A 33990be7e858
ux-story-gen is a command published in the GitHub repository Islanders-Treasure0969/claude-pilot (2 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 1,182 once invoked, about $0.0001 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.