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 skills add HK-hub/AgentSkills --skill redis-developmentgit clone --depth 1 https://github.com/HK-hub/AgentSkillsWrote 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/skills/hk-hub/agentskills/redis-development)<a href="https://agentmods.dev/skills/hk-hub/agentskills/redis-development"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/redis-development/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/skills/hk-hub/agentskills/redis-development"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/redis-development.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 | $0.00044 | $0.01079 |
| Opus 5 | $0.00022 | $0.00540 |
| Sonnet 5 | $0.00009 | $0.00216 |
| Haiku 4.5 | $0.00004 | $0.00108 |
Grade A, and why
redis-development 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 8d 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.
This is a copy
92% identical to redis-development — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Redis Best Practices
Comprehensive performance optimization guide for Redis, including Redis Query Engine, vector search, and semantic caching. Contains 29 rules across 11 categories, prioritized by impact to guide automated optimization and code generation.
When to Apply
Reference these guidelines when:
- Designing Redis data models and key structures
- Implementing caching, sessions, or real-time features
- Using Redis Query Engine (FT.CREATE, FT.SEARCH, FT.AGGREGATE)
- Building vector search or RAG applications with RedisVL
- Implementing semantic caching with LangCache
- Optimizing Redis performance and memory usage
Rule Categories by Priority
| Priority | Category | Impact | Prefix |
|---|---|---|---|
| 1 | Data Structures & Keys | HIGH | data- |
| 2 | Memory & Expiration | HIGH | ram- |
| 3 | Connection & Performance | HIGH | conn- |
| 4 | JSON Documents | MEDIUM | json- |
| 5 | Redis Query Engine | HIGH | rqe- |
| 6 | Vector Search & RedisVL | HIGH | vector- |
| 7 | Semantic Caching | MEDIUM | semantic-cache- |
| 8 | Streams & Pub/Sub | MEDIUM | stream- |
| 9 | Clustering & Replication | MEDIUM | cluster- |
| 10 | Security | HIGH | security- |
| 11 | Observability | MEDIUM | observe- |
Quick Reference
1. Data Structures & Keys (HIGH)
data-choose-structure- Choose the Right Data Structuredata-key-naming- Use Consistent Key Naming Conventions
2. Memory & Expiration (HIGH)
ram-limits- Configure Memory Limits and Eviction Policiesram-ttl- Set TTL on Cache Keys
3. Connection & Performance (HIGH)
conn-blocking- Avoid Slow Commands in Productionconn-pipelining- Use Pipelining for Bulk Operationsconn-pooling- Use Connection Pooling or Multiplexingconn-timeouts- Configure Connection Timeouts
4. JSON Documents (MEDIUM)
json-partial-updates- Use JSON Paths for Partial Updatesjson-vs-hash- Choose JSON vs Hash Appropriately
5. Redis Query Engine (HIGH)
What ships with it
41 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- AGENTS.md 63 KB
- assets/logo.png 21 KB
- metadata.json 600 B
- README.md 3.0 KB
- rules/_contributing.md 2.2 KB
- rules/_sections.md 1.7 KB
- rules/_template.md 1.5 KB
- rules/cluster-hash-tags.md 2.7 KB
- rules/cluster-read-replicas.md 1.4 KB
- rules/conn-blocking.md 2.0 KB
- rules/conn-client-cache.md 2.3 KB
- rules/conn-pipelining.md 1.3 KB
- rules/conn-pooling.md 2.1 KB
- rules/conn-timeouts.md 1.6 KB
- rules/data-choose-structure.md 2.6 KB
- rules/data-hash-field-expiry.md 2.0 KB
- rules/data-incr.md 2.1 KB
- rules/data-key-naming.md 1.7 KB
- rules/data-transactions.md 2.5 KB
- rules/json-partial-updates.md 1.4 KB
- rules/json-vs-hash.md 3.6 KB
- rules/observe-commands.md 1.1 KB
- rules/observe-metrics.md 1.4 KB
- rules/ram-limits.md 1.4 KB
- rules/ram-ttl.md 1.3 KB
- rules/rqe-dialect.md 1.3 KB
- rules/rqe-field-types.md 2.3 KB
- rules/rqe-index-creation.md 1.8 KB
- rules/rqe-index-management.md 1.1 KB
- rules/rqe-query-optimization.md 1.2 KB
- rules/rqe-skip-initial-scan.md 2.6 KB
- rules/security-acls.md 1.1 KB
- rules/security-auth.md 1.9 KB
- rules/security-network.md 1.1 KB
- rules/semantic-cache-best-practices.md 1.9 KB
- rules/semantic-cache-langcache-usage.md 2.3 KB
- rules/stream-choosing-pattern.md 1.3 KB
- rules/vector-algorithm-choice.md 2.0 KB
- rules/vector-hybrid-search.md 1.4 KB
- rules/vector-index-creation.md 2.1 KB
- rules/vector-rag-pattern.md 1.5 KB
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.
- 8d ago First seen · 122 lines · 44 tokens per session scan A 42463c02a0d6
redis-development is a skill published in the GitHub repository HK-hub/AgentSkills (6 stars, last pushed 24d ago), licensed MIT. It adds 44 tokens to every session and 1,079 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to redis-development, differing in 3 lines, and is treated as a copy.
Other skills, from other repositories
pinecone
Managed vector DB for production RAG and search.
vector-db
Vector database expert for embeddings, similarity search, RAG patterns, and indexing strategies.
qdrant-scaling-query-volume
Guides Qdrant query volume scaling. Use when someone asks 'query returns too many results', 'scroll performance', 'large limit values', 'paginating search results', 'fetching many vectors', or 'high cardinality results'.
Embedding Generator
Generate and manage text embeddings for semantic search, clustering, and similarity tasks.
pinecone
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.