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/adding-new-features)<a href="https://agentmods.dev/rules/eliornl/rolemule/adding-new-features"><img src="https://agentmods.dev/badge/rules/eliornl/rolemule/adding-new-features/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/adding-new-features"><img src="https://agentmods.dev/badge/rules/eliornl/rolemule/adding-new-features.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 | $0.00016 | $0.03499 |
| Opus 5.5 | $0.00006 | $0.01400 |
| Sonnet 5.5 | $0.00003 | $0.00700 |
| Haiku 4.5 | $0.00002 | $0.00350 |
Grade A, and why
adding-new-features 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding New Features — Checklists
New API Endpoint
- Add Pydantic request/response models
- Add route handler with
Depends(get_current_user)+Depends(get_database) - Check ownership — verify the resource belongs to
current_user - Apply rate limiting for sensitive or expensive operations
- Log operations with
logger.info(), errors withlogger.error() - Use
APIError/create_error_responsefor all errors — never bareHTTPException - Register router in
main.pyunder/api/v1/prefix - If the endpoint is also in the legacy
/api/prefix, addinclude_in_schema=False - Add API integration tests in
tests/test_api/usingauthed_client(mocked user) orauthed_client_with_user(real DB user) as appropriate - Add E2E mocked coverage in
api-validation.spec.ts— add a test that mocks the endpoint and verifies the frontend renders its response without JS errors - If the endpoint returns 429, add a matching test in
rate-limit.spec.ts
Workflow start — duplicate detection (POST /api/v1/workflow/start)
Before changing how jobs are keyed or deduplicated:
api/workflow.py—_find_duplicate_active_application/_fingerprint_job_content/_canonical_job_url;normalize_title_company_keyisutils/application_dedupe.py(imported where needed). Duplicate responses useRES_3002(409) and must releaseworkflow_creating:{user_id}on that path.- Fingerprint — stored on
WorkflowSession.job_input_data["content_fingerprint"]only when normalized text length ≥ 80 (constant_MIN_JOB_CONTENT_FINGERPRINT_CHARS). Do not weaken NFKC / zero-width stripping without re-checking extension vs paste dedupe. - Post-start duplicate handling — see
rolemule-core.mdc§ Duplicate job after start (find_conflicting_job_applicationinutils/application_dedupe.py,_maybe_fail_duplicate_job_after_analyzerinworkflows/job_application_workflow.py, integrity handling inapi/workflow.py_update_job_application_with_final_state). - Tests — extend
tests/test_api/test_workflow.pyandtests/test_application_dedupe.pyas appropriate; frontend must handleRES_3002inui/src/pages/dashboard-new-application.ts,ui/src/shared/api.ts, and the Chrome extension (popup.js,service-worker.js). - Docs —
rolemule-core.mdc§RES_3002and § Duplicate job after start;dashboard-home.mdc§ Toast Deduplication —notifyReady(c:/f:keys vs legacy baresessionId).
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 · 197 lines · 16 tokens per session scan A 0f9071c17696
adding-new-features is a cursor rule published in the GitHub repository eliornl/rolemule (38 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 3,499 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
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.