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.
npx agentmods add rules/eliornl/rolemule/caching-redisgit clone --depth 1 https://github.com/eliornl/rolemuleWhat 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 | $0.00000 | $0.02319 |
| Opus 5 | $0.00000 | $0.01159 |
| Sonnet 5 | $0.00000 | $0.00464 |
| Haiku 4.5 | $0.00000 | $0.00232 |
Grade A, and why
caching-redis 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 2d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Caching & Rate Limiting Patterns
Cache Schema Version
All keys are prefixed with CACHE_VERSION (currently v1). Bump CACHE_VERSION in utils/cache.py to instantly flush all caches on deploy — old keys expire via TTL.
Cache TTLs and Key Patterns
| Cache | TTL | Key pattern |
|---|---|---|
| Job analysis | 24h | v1:job_analysis:{hash} — hash includes URL + up to 50,000 chars of normalized job text (_MAX_JOB_CONTENT_FOR_CACHE_KEY in utils/cache.py) so different listings on the same long page do not share one cache entry |
| Company research | 7d | v1:company_research:{hash}:{name} |
| User profile | 5min | v1:user_profile:{uuid} |
| Workflow state | 1min | v1:workflow_state:{session_id} |
| LLM response | 1h | v1:llm_response:{user_id}:{hash} (user-scoped) or v1:llm_response:{hash} (shared) |
| Interview prep | 7d | v1:interview_prep:{session_id} |
| Hiring outreach | 7d | v1:hiring_outreach:{session_id} |
| Hiring outreach generating | 10min | v1:hiring_outreach_generating:{session_id} — atomic SET NX lock |
| CV optimization result | 24h | v1:cv_optimization:{session_id} — get_cached_cv_optimization() unwraps cache_set {"data": ...} wrapper |
| CV optimization running | 30min | v1:cv_optimization_running:{session_id} — atomic SET NX lock |
| Mock interview thinking | 3min | v1:mock_interview_thinking:{session_id} — atomic SET NX turn lock |
| Tool result | 1h | v1:tool_result:{tool_name}:{hash} |
Auth-Specific Redis Keys (managed by api/auth.py and utils/auth.py)
These keys are not versioned with CACHE_VERSION — do not flush them as part of cache invalidation.
| Purpose | TTL | Key pattern |
|---|---|---|
| JWT revocation blocklist | Remaining token lifetime + 60 s | jwt_blocklist:{jti} |
| OAuth CSRF state | 10 min | oauth_state:{state_token} |
| OAuth one-time exchange code | 30 s | oauth_code:{code} |
| Password reset token | 1 h | password_reset:{token} |
| Email verification code | 15 min | email_verification:{code} |
| Email verification current-code pointer | 15 min | email_verification_user:{email} |
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.
- 2d ago First seen · 185 lines · 2,319 tokens per session scan A fc9e71af6529
caching-redis is a cursor rule published in the GitHub repository eliornl/rolemule (37 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,319 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
cursorrules
Agent2 is a framework for building production AI agents with typed HTTP APIs. PydanticAI handles the agent loop. Agent2 handles everything else: API, auth, pause/resume, approvals, provider routing, knowledge search.
product-manager
Holistic product leader who owns the full product lifecycle — from discovery and strategy through roadmap, stakeholder alignment, go-to-market, and outcome measurement. Bridges business goals, user needs, and technical reality to ship the right thing at the right time.
developer-advocate
Expert developer advocate specializing in building developer communities, creating compelling technical content, optimizing developer experience (DX), and driving platform adoption through authentic engineering engagement. Bridges product and engineering teams with external developers.
api-tester
Expert API testing specialist focused on comprehensive API validation, performance testing, and quality assurance across all systems and third-party integrations.
architectural-and-structural-rules
The project follows a layered architecture with clear separation of concerns.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.