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 nimadorostkar/Claude-Skills-collection --skill cachinggit clone --depth 1 https://github.com/nimadorostkar/Claude-Skills-collectionWrote 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/nimadorostkar/claude-skills-collection/caching)<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/caching"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/caching/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/nimadorostkar/claude-skills-collection/caching"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/caching.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.01074 |
| Opus 5 | $0.00017 | $0.00537 |
| Sonnet 5 | $0.00007 | $0.00215 |
| Haiku 4.5 | $0.00003 | $0.00107 |
Grade A, and why
caching 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 12d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Caching
Purpose
Add a cache with a clear invalidation story, or find out why the existing one is serving stale data. A cache is a second source of truth; introducing one is a consistency decision, not just a performance one.
When to Use
- A read path is slow and the data is read far more often than it is written.
- An upstream dependency is expensive, rate-limited, or unreliable.
- Debugging stale reads, cache stampedes, or unexplained memory growth.
Capabilities
- Cache placement: client, CDN, application, database.
- Strategies: cache-aside, read-through, write-through, write-behind.
- Invalidation: TTL, explicit, event-driven, versioned keys.
- Stampede protection: locking, early recomputation, request coalescing.
- Negative caching and hot-key mitigation.
Inputs
- The read/write ratio and the cost of the uncached path.
- How stale the data is allowed to be — in seconds, agreed with the product owner.
- Cardinality of the key space and expected memory footprint.
Outputs
- A key schema, a TTL, and an invalidation trigger for each cached entity.
- Stampede protection on any key expensive enough to matter.
- A hit-rate metric, because a cache you do not measure is a cache you do not understand.
Workflow
- Prove the need — Measure the uncached path first. A cache in front of a missing index is a permanent workaround for a five-minute fix.
- Decide the staleness budget — Ask what breaks if a user sees data five seconds old. The answer determines the TTL and whether you need explicit invalidation.
- Design the key — Include everything that varies the result: tenant, locale, permission scope. A key that omits a dimension leaks data between users.
- Choose invalidation — TTL alone for tolerant data. TTL plus explicit deletion on write for data that must be fresh. Versioned keys when deletion is unreliable.
- Protect against stampedes — When a hot key expires, every concurrent request misses simultaneously and hits the origin at once. Use a lock or single-flight.
- Measure — Hit rate, latency at each layer, and eviction rate. Falling hit rate with rising memory means the key space is too large.
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.
- 12d ago First seen · 95 lines · 34 tokens per session scan A c9d0b1485682
caching is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (26 stars, last pushed 25d ago), licensed MIT. It adds 34 tokens to every session and 1,074 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
google-cloud-storage-fuse
Mounts Cloud Storage buckets as a POSIX file system with Cloud Storage FUSE (gcsfuse). Use when interacting with gcsfuse: decide whether FUSE, native gs:// reads, or Filestore/Managed Lustre fits a workload, deploy tuned mounts on GKE, Compute Engine, or Cloud Run, enable and size file, stat, and list caches, tune…
offensive-sqli
SQL injection testing skill for offensive security assessments and bug bounty hunting. Covers error-based, UNION-based, boolean/time-based blind, out-of-band, second-order, NoSQL, GraphQL, WebSocket, and JSON-operator SQLi. Includes WAF bypass techniques, database-specific exploitation (MySQL, MSSQL, PostgreSQL…
aws-cloudformation-elasticache
Provides AWS CloudFormation patterns for ElastiCache Redis or Memcached infrastructure, including subnet groups, parameter groups, security controls, and cross-stack outputs. Use when designing cache tiers, high-availability replication groups, encryption settings, or reusable CloudFormation templates for application…
spring-boot-cache
Provides patterns for implementing Spring Boot caching: configures Redis/Caffeine/EhCache providers with TTL and eviction policies, applies @Cacheable/@CacheEvict/@CachePut annotations, validates cache hit/miss behavior, and exposes metrics via Actuator. Use when adding caching to Spring Boot services, configuring…
caching-strategies
CDN, Redis, in-memory cache, cache invalidation, and distributed caching patterns.
hermes-mnemosyne
Mnemosyne is Hermes' primary local-first memory engine — SQLite with vector + FTS5 hybrid search, 19+ tools, auto-consolidation, and a standalone CLI. It's a pip-installed plugin (not a built-in toolset) discovered via $HERMESHOME/plugins/mnemosyne/.