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 G1Joshi/Agent-Skills --skill memcachedgit clone --depth 1 https://github.com/G1Joshi/Agent-SkillsWrote 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/g1joshi/agent-skills/memcached)<a href="https://agentmods.dev/skills/g1joshi/agent-skills/memcached"><img src="https://agentmods.dev/badge/skills/g1joshi/agent-skills/memcached.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.00373 |
| Opus 5 | $0.00007 | $0.00187 |
| Sonnet 5 | $0.00003 | $0.00075 |
| Haiku 4.5 | $0.00001 | $0.00037 |
Grade A, and why
memcached 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 5d 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.
What it actually says
Memcached
Memcached is a high-performance, distributed memory object caching system. It is simpler than Redis. It does arguably one thing: Key-Value caching of strings/objects in RAM.
When to Use
- Simple Caching: Pure LRU cache.
- Multi-Threaded: Memcached is multi-threaded (Redis is single-threaded). It scales vertically better on massive multicore machines for simple GET/SET throughput.
- Session Cache: Storing web sessions.
Quick Start
# Telnet interface
set mykey 0 60 4
data
STORED
get mykey
VALUE mykey 0 4
data
END
Core Concepts
Slab Allocation
Memcached manages memory in "Classes" of chunks (Slabs) to prevent fragmentation.
LRU (Least Recently Used)
When full, it evicts the oldest unused items.
No Persistence
If you restart, data is gone.
Best Practices (2025)
Do:
- Use for huge read-heavy loads: Facebook uses it heavily.
- Use Serialization: Store Protobuf or msgpack for efficiency.
Don't:
- Don't use as a Datastore: It is a cache only.
- Don't use iterating: You cannot "List all keys". You must know the key to get the value.
- Comparison to Redis: In 2025, Redis is generally preferred for features. Use Memcached if you specifically need multi-threaded scaling for pure String caching.
References
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.
- 5d ago First seen · 60 lines · 14 tokens per session scan A 664ef0d79b23
memcached is a skill published in the GitHub repository G1Joshi/Agent-Skills (12 stars, last pushed 7mo ago), licensed MIT. It adds 14 tokens to every session and 373 once invoked, about $0.0001 per session on Opus 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 2026-09-03.
Other skills, from other repositories
redis-operations
Redis operational runbooks — memory management, eviction policy, persistence config, Sentinel/Cluster, K8s-hosted Redis ops.
redis-caching-and-pubsub
Architecting high-performance caching strategies, Cache-Aside/Write-Through/Write-Behind patterns, Redis Pub/Sub, Streams, eviction policies, distributed locking (Redlock), and memory optimization. Use when implementing Redis caching, real-time messaging, rate limiting, or session management.
pinecone
Managed vector DB for production RAG and search.
deprecation-and-migration
Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset…
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'.
edge-serverless-db-expert
Expert guide for Serverless & Edge Databases (Neon Serverless Postgres, Cloudflare D1, Turso/libsql, Upstash Redis), cold-start mitigation, and connection pooling / Panduan ahli database Serverless & Edge (Neon, Cloudflare D1, Turso, Upstash).