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 mercuryPark/oc-setup --skill caching-strategygit clone --depth 1 https://github.com/mercuryPark/oc-setupWrote 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/mercurypark/oc-setup/caching-strategy)<a href="https://agentmods.dev/skills/mercurypark/oc-setup/caching-strategy"><img src="https://agentmods.dev/badge/skills/mercurypark/oc-setup/caching-strategy/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/mercurypark/oc-setup/caching-strategy"><img src="https://agentmods.dev/badge/skills/mercurypark/oc-setup/caching-strategy.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 | $0.00027 | $0.00308 |
| Opus 5.5 | $0.00011 | $0.00123 |
| Sonnet 5.5 | $0.00005 | $0.00062 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
caching-strategy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Caching Strategy
Multi-Layer Caching
Browser Cache
Cache-Control: public, max-age=3600
ETag: "abc123"
CDN Cache
- Cache static assets at edge
- Purge via API on deployments
- Use versioned filenames
Application Cache (Redis)
const cacheKey = `user:${userId}`
let user = await redis.get(cacheKey)
if (!user) {
user = await db.query('SELECT * FROM users WHERE id = $1', [userId])
await redis.setex(cacheKey, 3600, JSON.stringify(user))
}
Cache Invalidation
Strategies
- Time-based: TTL
- Event-based: On data change
- Version-based: Increment version key
Pattern: Cache-aside
async function getUser(id: string) {
const cached = await cache.get(id)
if (cached) return cached
const user = await db.get(id)
await cache.set(id, user, 3600)
return user
}
Best Practices
- Set appropriate TTL based on data volatility
- Implement cache warming for critical data
- Monitor cache hit rates
- Handle cache failures gracefully (fallback to DB)
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.
- 2mo ago First seen · 57 lines · 27 tokens per session scan A 97f0a5fdc1ff
caching-strategy is a skill published in the GitHub repository mercuryPark/oc-setup (2 stars, last pushed 6mo ago), licensed MIT. It adds 27 tokens to every session and 308 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 2026-08-31.
Other skills, from other repositories
haven-db
Reset, reseed, locate and prune a haven stack's databases with haven db, and know which verbs destroy data. Use when someone says 'haven db', 'reset the database', 'drop the database', 'reseed in place', 'db preset', 'demo preset', 'database url', 'connection string for postgres', 'haven db prune', 'haven seed'…
redis-js
Work with the Upstash Redis JavaScript/TypeScript SDK for serverless Redis operations. Use for caching, session storage, rate limiting, leaderboards, full-text search (querying, filtering, aggregating with @upstash/redis search extension), and all Redis data structures. Supports automatic serialization/deserialization…
using-redis-token-buckets
Use when adding a bucket-like rate limit backed by Redis: a per-caller budget with burst capacity and continuous refill, a refund path for requests that did no work, or a limit whose Retry-After must be a real wait rather than a window edge. posthog/tokenbucket.py provides an atomic Lua token bucket (consume, refund…
byted-milvus
Manages Milvus on Volcano Engine (Volcengine): provision/inspect/scale/delete clusters and run collection + CRUD/search operations via bundled CLIs. Use when the user mentions Milvus + Volcengine/Volcano Engine or asks to operate Milvus there.
bex-keyvalue
Provisions and configures bex Key Value (Redis-compatible Valkey 8) instances for caching, session storage, and job queues. Use when the user needs Key Value, uses Redis or Valkey, or needs a cache, session store, or job queue backend, or needs to configure maxmemory policy, ipAllowList, connection strings, or…
background-job-orchestrator
Expert in background job processing with Bull/BullMQ (Redis), Celery, and cloud queues. Implements retries, scheduling, priority queues, and worker management. Use for async task processing, email campaigns, report generation, batch operations. Activate on "background job", "async task", "queue", "worker", "BullMQ"…