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/eliornl/rolemuleWrote 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/rules/eliornl/rolemule/ui-application-detail)<a href="https://agentmods.dev/rules/eliornl/rolemule/ui-application-detail"><img src="https://agentmods.dev/badge/rules/eliornl/rolemule/ui-application-detail/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/rules/eliornl/rolemule/ui-application-detail"><img src="https://agentmods.dev/badge/rules/eliornl/rolemule/ui-application-detail.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 | $0.09220 |
| Opus 5.5 | $0.00000 | $0.03688 |
| Sonnet 5.5 | $0.00000 | $0.01844 |
| Haiku 4.5 | $0.00000 | $0.00922 |
Grade A, and why
ui-application-detail 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.
How it starts
The opening of the file, as written. The whole thing — 677 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Application Detail Page
Tab Architecture
Tab order (left to right): Job Details → Your Fit → Strategy → Company → Cover Letter → Resume → Optimize CV → Interview → Mock Session → Outreach
| Tab | Pane ID | Container | Sub-tabs? |
|---|---|---|---|
| Job Details | pane-jobdetails |
#jobDetailsContent |
No |
| Your Fit | pane-fit |
#fitContent |
No |
| Strategy | pane-strategy |
#strategyContent |
No |
| Company | pane-company |
#companyContent |
No |
| Cover Letter | pane-cover |
#coverContent |
No |
| Resume | pane-resume |
#resumeContent |
Yes: Overview, Experience, Keywords & ATS, Summary |
| Optimize CV | pane-optimize |
#cvOptimizeContent |
No — see cv-optimizer-feature.mdc |
| Interview | pane-interview |
#interviewContent |
Yes: Process, Questions, Preparation |
| Mock Session | pane-practice |
#mockInterviewContent |
No — see mock-interview-feature.mdc |
| Outreach | pane-outreach |
#ho-setup / #ho-progress / #ho-results |
No — see hiring-outreach-feature.mdc |
First active tab is jobdetails (not company). pane-jobdetails carries the active class in HTML. Page tab bar uses 10-column CSS grid.
Mock Session Tab
Conversational mock interview (HR / Pro / Manager; 10/15/20 minutes). Browser STT/TTS with typed fallback. See mock-interview-feature.mdc.
ui/src/pages/application-detail.ts calls window.initMockInterviewTab(currentSessionId) on data-tab="practice".
Sections: #mi-setup, #mi-active, #mi-results. Setup uses flex → require #mi-setup.mi-setup-empty.is-hidden { display: none; }.
UI aligns with Optimize CV: centered empty-state + config selects + AI Setup warning; live session uses apply-decision-banner + content-section + regen-btn / cl-copy-btn; debrief uses results banner + score chips.
Outreach Tab
Public web contact finder + copy-only draft messages (no send integration, no professional networking profile links). See hiring-outreach-feature.mdc.
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 · 677 lines · 0 tokens per session scan A c91924cd1a23
ui-application-detail is a cursor rule published in the GitHub repository eliornl/rolemule (38 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 9,220 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
shared-plane-packages
Pattern for creating shared plane packages that serve both migration and runtime planes.