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 cosmix/loom --skill loom-cachinggit clone --depth 1 https://github.com/cosmix/loomWrote 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/cosmix/loom/loom-caching)<a href="https://agentmods.dev/skills/cosmix/loom/loom-caching"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-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/cosmix/loom/loom-caching"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-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 | $0.00031 | $0.03286 |
| Opus 5.5 | $0.00012 | $0.01314 |
| Sonnet 5.5 | $0.00006 | $0.00657 |
| Haiku 4.5 | $0.00003 | $0.00329 |
Grade A, and why
loom-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 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.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Caching
Overview
Store expensive-to-compute or frequently-read data closer to the consumer. The easy part is the read path; the hard parts are invalidation (keeping it correct) and stampede (surviving a mass miss). This skill is organized around those failure modes, not around toy get/set wrappers.
Strategy Selection
| Strategy | Read path | Write path | Consistency | Failure mode to watch |
|---|---|---|---|---|
| Cache-aside (lazy) | App checks cache → loads on miss → populates | App writes DB, then invalidates (don't update) cache | Eventual; brief staleness window | Stampede on hot-key miss; race between load and invalidate |
| Read-through | Cache library loads on miss | (paired with write-through) | Eventual | Same as aside; hides loader in the cache layer |
| Write-through | Read from cache | Write DB and cache synchronously | Strong-ish; cache always fresh after write | Write latency = DB + cache; cache churn for rarely-read keys |
| Write-behind (write-back) | Read from cache | Write cache now, flush DB async in batches | Weak; data loss if node dies before flush | Lost writes on crash; ordering; DB divergence |
Default to cache-aside. It's simple, resilient (cache down ≠ writes fail), and puts invalidation in your control. Reach for write-through only when you can't tolerate a post-write stale read; write-behind only for write-heavy, loss-tolerant data (metrics, counters, activity feeds).
⚠ On write, invalidate — do not update — the cache (cache-aside). Two concurrent writers updating the cache can commit their DB writes in one order and their cache writes in the opposite order, leaving the cache permanently wrong. Deleting the entry forces the next reader to reload the DB's truth. (This is the [Facebook "leases"] class of bug.)
⚠ Write-behind loses data. A crash between "wrote cache" and "flushed DB" silently drops the write. Never use it as the system of record for anything you can't recompute or afford to lose.
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 Changed · -23 tokens per session ef1f4f177e06
- 1mo ago First seen · 196 lines · 54 tokens per session scan A 2e0635220491
loom-caching is a skill published in the GitHub repository cosmix/loom (62 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 3,286 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 2026-08-30.
Other skills, from other repositories
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…
build-feature-store
Build a feature store using Feast for centralized feature management, configure offline and online stores for batch and real-time serving, define feature views with transformations, and implement point-in-time correct joins for ML pipelines. Use when managing features for multiple ML models, ensuring training-serving…
domainmodel-dsl
Read, write, and modify Domain Model DSL files (.dmodel) — datatypes, entities with inheritance and multi-valued features, and nested packages with qualified cross-references. Use when the user wants to create, edit, explain, or debug a domain model in this DSL, including resolving references across packages.
domainmodel-dsl
Work with the Domain Model DSL (.dmodel) for describing data models — datatypes, entities, and their features. Use when the user wants to create or edit a domain model in this DSL.
google-cloud-storage-fuse
Mounts Cloud Storage buckets on Google Cloud as a POSIX file system using Cloud Storage FUSE (and the gcsfuse CLI tool). Use when interacting with the gcsfuse CLI or Cloud Storage FUSE mounts: decide whether FUSE, native gs:// reads, or Filestore/Managed Lustre fits a workload, deploy tuned mounts on GKE, Compute…