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/dashboard-home)<a href="https://agentmods.dev/rules/eliornl/rolemule/dashboard-home"><img src="https://agentmods.dev/badge/rules/eliornl/rolemule/dashboard-home/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/dashboard-home"><img src="https://agentmods.dev/badge/rules/eliornl/rolemule/dashboard-home.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 | $0.07760 |
| Opus 5.5 | $0.00000 | $0.03104 |
| Sonnet 5.5 | $0.00000 | $0.01552 |
| Haiku 4.5 | $0.00000 | $0.00776 |
Grade A, and why
dashboard-home 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 — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dashboard Home (/dashboard)
ui/dashboard/index.html + ui/src/pages/dashboard-home.ts
The dashboard home is the only application list page. /dashboard/history was permanently removed — do not re-add it. All filtering, sorting, searching, and bulk operations live here.
API — GET /api/v1/applications/
| Param | Type | Notes |
|---|---|---|
search |
str (max 200) |
Case-insensitive LIKE across job_title AND company_name (OR). Takes priority over company. |
status_filter |
str |
Case-insensitive status match. Values: PROCESSING, COMPLETED, APPLIED, INTERVIEW, REJECTED, ACCEPTED. |
days |
int (1–365) |
Filter by last N days (based on created_at). |
sort |
str |
created_desc (default) | created_asc | updated_desc | company_asc | title_asc |
page |
int (≥1) |
Page number (1-indexed). |
per_page |
int (1–100) |
Results per page (default 20). |
company |
str (max 200) |
Legacy company-name filter; ignored when search is also present. |
The backend uses func.lower().contains() (parameterised — no SQL injection risk). Unknown sort values silently fall back to created_desc.
List + stats visibility (_dashboard_application_visibility_filter)
GET /api/v1/applications/ and GET /api/v1/applications/stats/overview outerjoin workflow_sessions on job_applications.session_id and exclude rows where workflow_sessions.workflow_status = 'failed' (in addition to deleted_at IS NULL and job_applications.status != 'failed').
Why: job_applications can remain processing for a short window after the workflow session is already failed, while _format_application_response() maps that pair to a failed badge for the API consumer — which used to show a phantom FAILED card. Filtering on workflow status keeps failed analyses off the list and aligns counts with the empty state. See rolemule-core.mdc (workflow failure — no partial client data).
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 · 455 lines · 0 tokens per session scan A 1ca876eb274c
dashboard-home is a cursor rule published in the GitHub repository eliornl/rolemule (38 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,760 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
development
Development environment setup and commands for backend services.
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.