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 tonone-ai/tonone --skill cache-evictgit clone --depth 1 https://github.com/tonone-ai/tononeWrote 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/tonone-ai/tonone/cache-evict)<a href="https://agentmods.dev/skills/tonone-ai/tonone/cache-evict"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/cache-evict/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/tonone-ai/tonone/cache-evict"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/cache-evict.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 | $0.00050 | $0.00367 |
| Opus 5.5 | $0.00020 | $0.00147 |
| Sonnet 5.5 | $0.00010 | $0.00073 |
| Haiku 4.5 | $0.00005 | $0.00037 |
Grade A, and why
cache-evict 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 1mo 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
88% identical to cache-design — 12 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.
What it actually says
Cache Evict
You are Cache — Caching Strategy Engineer on the Infrastructure Specialist Team.
Steps
Step 0: Confirm Context
Ask the user for any missing context needed to produce a useful output. If the request is clear, skip questions and proceed.
Step 1: Gather Context
Gather cached data relationships, write patterns, and consistency requirements.
Step 2: Produce Output
Output an invalidation strategy: invalidation trigger design (event-driven vs TTL), thundering herd mitigation, key versioning approach, and cache warming plan.
Step 3: Summary
Output a brief summary:
- What was produced
- Key risks or tradeoffs
- Recommended next steps
Key Rules
- Follow the output format defined in docs/output-kit.md
- Always quantify tradeoffs: cost, reliability, and operational complexity
- Flag when recommendation requires production validation or load testing
Delivery
If output exceeds the 40-line CLI budget, invoke /atlas-report with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.
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.
- 1mo ago First seen · 47 lines · 50 tokens per session scan A 5c183571f696
cache-evict is a skill published in the GitHub repository tonone-ai/tonone (76 stars, last pushed 10d ago), licensed MIT. It adds 50 tokens to every session and 367 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to cache-design, differing in 12 lines, and is treated as a copy.
Other skills, from other repositories
build-with-opengeni
Add Opengeni agents to the user's own product, backend, website, or app with @opengeni/sdk and @opengeni/react: the packaged chat UI behind one server route, per-tenant workspaces, and the product's own tools. Also builds a small local demo web app with an Opengeni chat. Use when the user wants AI agents or an…
backend-caching
Use this skill when the user says 'cache', 'Redis', 'Memcached', 'CDN', 'cache-aside', 'read-through', 'write-through', 'write-behind', 'cache invalidation', 'TTL', 'cache stampede', 'thundering herd', 'cache warming', 'LRU', 'LFU', 'cache hit ratio', 'cache strategy', or when designing a caching layer. This skill…
agentmail-v2
AgentMail — Email for AI Agents workflow skill. Use this skill when the user needs Email infrastructure for AI agents. Create accounts, send/receive emails, manage webhooks, and check karma balance via the AgentMail API and the operator should preserve the upstream workflow, copied support files, and provenance before…
service-explorer
Discover and interact with ANY service running on the system. Not pre-programmed per-service. Discovers dynamically. Read configs, hit APIs, parse logs. Figure it out.
elasticsearch-authn
Authenticate to Elasticsearch using native, file-based, LDAP/AD, SAML, OIDC, Kerberos, JWT, or certificate realms. Use when connecting with credentials, choosing a realm, or managing API keys.
kafka
Kafka topic management, consumer group monitoring, message production/consumption, and cluster health diagnostics. Use when working with Kafka brokers, topics, consumer lag, or debugging pipeline issues.