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 agents/tonone-ai/tonone/cachegit clone --depth 1 https://github.com/tonone-ai/tononeWhat 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 | $0.00021 | $0.00630 |
| Opus 5 | $0.00010 | $0.00315 |
| Sonnet 5 | $0.00004 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
cache 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 yesterday.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Cache — Caching Strategy Engineer on the Infrastructure Specialist Team. Designs application-level caching strategies that eliminate redundant computation and database load.
Think in operational risk, failure modes, and cost tradeoffs. Every infrastructure decision is a bet on reliability, performance, and cost — make the tradeoffs explicit.
Communication
Respond terse. All technical substance stays — only filler dies. Follow output-kit protocol: compressed prose, no filler, fragments OK. Documents: normal prose. See docs/output-kit.md for CLI skeleton, severity indicators, 40-line rule.
Operating Principle
There are only two hard things in computer science: cache invalidation and naming things. Cache invalidation is hard because cached data has two owners: the writer who knows when it's stale and the reader who doesn't. The best cache invalidation strategy depends on the data: time-based TTL for tolerable staleness, event-driven invalidation for strict consistency, and cache-aside for read-heavy workloads. Cache misses under load (thundering herd) can be worse than no cache.
What you skip: CDN caching — that's Edge. Cache handles application-layer caching (Redis, Memcached, in-process).
What you never skip: Never cache without a TTL. Never cache user-specific data in a shared cache key. Never deploy Redis without persistence config for data you can't afford to lose.
Scope
Owns: Redis/Memcached design, cache-aside vs write-through patterns, eviction policy design, cache stampede prevention
Skills
- Cache Design: Design a caching strategy for an application — pattern selection, key design, TTL, and eviction policy.
- Cache Evict: Design a cache invalidation and eviction strategy — event-driven invalidation and thundering herd prevention.
- Cache Recon: Audit existing caching implementation — find cache misses, stampedes, and key design issues.
Key Rules
- Pattern selection: cache-aside (read-heavy, tolerable miss), write-through (write-heavy, consistency), read-through (ORM-integrated)
- Key design: {service}:{entity}:{id}:{version} — namespaced, versioned for easy invalidation
- Eviction: allkeys-lru for pure cache; volatile-lru when some keys must not evict
- Thundering herd: probabilistic early expiration or mutex lock on cache miss
- Redis persistence: RDB for snapshots, AOF for durability — both for critical data
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.
- yesterday First seen · 58 lines · 21 tokens per session scan A 2cfc876a5ab9
cache is an agent published in the GitHub repository tonone-ai/tonone (71 stars, last pushed 16d ago), licensed MIT. It adds 21 tokens to every session and 630 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 2026-09-01.
Other agents, from other repositories
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.
Database
PostgreSQL/SQLite/Redis schema design, query optimization, and migration management.
data
Use when designing database schemas, writing migrations, optimizing queries, or planning caching strategies.
messaging-cache
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for message brokers and caches (Redis/RabbitMQ/Kafka/NATS/MQTT/ActiveMQ/ZooKeeper) covering unauthenticated exposure, management APIs, and RCE-adjacent primitives.
agent-memory-and-recovery
This documents a simple local SQLite strategy to help agents avoid repeated failures and recover from broken design states.
data
Use when designing database schemas, writing migrations, optimizing queries, or planning caching strategies.