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 SalesforceCommerceCloud/b2c-developer-tooling --skill b2c-custom-cachesgit clone --depth 1 https://github.com/SalesforceCommerceCloud/b2c-developer-toolingWrote 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/salesforcecommercecloud/b2c-developer-tooling/b2c-custom-caches)<a href="https://agentmods.dev/skills/salesforcecommercecloud/b2c-developer-tooling/b2c-custom-caches"><img src="https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/b2c-custom-caches/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/salesforcecommercecloud/b2c-developer-tooling/b2c-custom-caches"><img src="https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/b2c-custom-caches.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 | $0.00088 | $0.01797 |
| Opus 5.5 | $0.00035 | $0.00719 |
| Sonnet 5.5 | $0.00018 | $0.00359 |
| Haiku 4.5 | $0.00009 | $0.00180 |
Grade A, and why
b2c-custom-caches 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
B2C Custom Caches
Custom caches improve code performance by storing data that is expensive to calculate, takes a long time to retrieve, or is accessed frequently. Caches are defined in JSON files within cartridges and accessed via the Script API.
When to Use Custom Caches
| Use Case | Example |
|---|---|
| Expensive calculations | Check if any variation product is on sale for base product display |
| External system responses | Cache in-store availability or prices from external APIs |
| Configuration settings | Store configuration data from JSON files or external sources |
| Frequently accessed data | Product attributes, category data, site preferences |
Limitations
| Constraint | Value |
|---|---|
| Total memory per app server | ~20 MB for all custom caches |
| Max caches per code version | 100 |
| Max entry size | 128 KB |
| Supported value types | Primitives, arrays, plain objects, null (not undefined) |
| Cross-server sync | None (caches are per-application-server) |
Defining a Custom Cache
File Structure
my_cartridge/
├── package.json # References caches.json
└── caches.json # Cache definitions
package.json
Add a caches entry pointing to the cache definition file:
{
"name": "my_cartridge",
"caches": "./caches.json"
}
caches.json
Define caches with unique IDs and optional expiration:
{
"caches": [
{
"id": "ProductAttributeCache"
},
{
"id": "ExternalPriceCache",
"expireAfterSeconds": 300
},
{
"id": "SiteConfigCache",
"expireAfterSeconds": 60
}
]
}
| Property | Required | Description |
|---|---|---|
id |
Yes | Unique ID across all cartridges in code version |
expireAfterSeconds |
No | Maximum seconds an entry is retained |
Using Custom Caches
Script API Classes
| Class | Description |
|---|---|
dw.system.CacheMgr |
Entry point for accessing defined caches |
dw.system.Cache |
Cache instance for storing and retrieving entries |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 280 lines · 88 tokens per session scan A 4532b4e1dd07
b2c-custom-caches is a skill published in the GitHub repository SalesforceCommerceCloud/b2c-developer-tooling (56 stars, last pushed today), licensed Apache-2.0. It adds 88 tokens to every session and 1,797 once invoked, about $0.0004 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
huawei-cloud-dds-dcs-instance-management
Huawei Cloud DDS (Document Database Service) and DCS (Distributed Cache Service) unified management skill. Provides 16 operations across five capability domains: (1) Query — list/get DDS/DCS instances, DCS node info, DCS custom templates; (2) Analysis — analyze DDS deployment architecture and DCS security posture; (3)…
brainctl
Unified agent memory CLI — read, write, search, and maintain the shared memory spine (brain.db). Use for persistent cross-session memory, knowledge graph, event logging, decisions, affect tracking, and consolidation.
redis
Skill "redis" from dhaupin/vant, covering redis, when to use, what to do, 1. connect and 2. operations.
quarry
Query PostgreSQL, MySQL, Redis and Neptune with Quarry (qy), compare data across environments, maintain reusable queries, and manage connections or the database workbench. Use for database evidence or explicit Quarry tasks, not general database design discussions.
redis
A guide to managing Redis, an in-memory database commonly used for fast data access, caching, counters, and temporary values.
bullmq-specialist
BullMQ expert for Redis-backed job queues, background processing, and reliable async execution in Node.js/TypeScript applications. Use when: bullmq, bull queue, redis queue, background job, job queue.