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 celigo/ai --skill configuring-lookup-cachesgit clone --depth 1 https://github.com/celigo/aiWrote 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/celigo/ai/configuring-lookup-caches)<a href="https://agentmods.dev/skills/celigo/ai/configuring-lookup-caches"><img src="https://agentmods.dev/badge/skills/celigo/ai/configuring-lookup-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/celigo/ai/configuring-lookup-caches"><img src="https://agentmods.dev/badge/skills/celigo/ai/configuring-lookup-caches.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk 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 | $0.00060 | $0.03797 |
| Opus 5 | $0.00030 | $0.01899 |
| Sonnet 5 | $0.00012 | $0.00759 |
| Haiku 4.5 | $0.00006 | $0.00380 |
Grade A, and why
configuring-lookup-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 9d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuring Lookup Caches
A lookup cache is an in-memory key-value store managed by Celigo for fast data retrieval during integration processing. Unlike export-based lookups that query external systems per-record, lookup caches provide sub-millisecond access to pre-loaded reference data without consuming API calls.
Lookup caches handle three concerns:
- Cache metadata -- name, integration scope, and whether data is included in templates/cloning
- Data management -- loading, retrieving, updating, and purging key-value entries via dedicated data endpoints
- Size governance -- each cache has a 50 MB limit; the per-environment aggregate limit across all caches is 1 GB
Lookup caches are consumed by import and export mappings via the lookups[] array. A lookup entry references a cache by _lookupCacheId and optionally extracts a specific field from the cached object via the extract JSON path. This is configured on the import/export resource, not on the cache itself.
Used across flows, APIs, and tools.
"Lookup" -- Which One Is Meant?
"Lookup" is overloaded in Celigo, and a lookup cache is only one thing the word can mean. When a request just says "the lookup," confirm which one before acting -- they live in different places and are configured differently. A single entry in lookups[] resolves its value one of three ways:
- Cached -- the entry sets
_lookupCacheIdto read a lookup cache (this skill): pre-loaded reference data read in-memory, no per-record external call, as fresh as the last data load. - Static map -- the entry carries an inline
mapobject. No cache and no external call; the table travels with the import/export. Best for a handful of stable pairs that rarely change. - Live / dynamic -- the entry issues a per-record query against a connected system (an HTTP request, SOQL, a NetSuite search, SQL). Always-fresh answers, at the cost of one external request per record.
Quick test for which is meant: pre-loaded data read in-memory is a lookup cache; an answer that must reflect the source system right now is a live/dynamic lookup; a small fixed table living on the step is a static map.
What ships with it
2 files 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.
- 9d ago First seen · 239 lines · 60 tokens per session scan A 83b97c44e812
configuring-lookup-caches is a skill published in the GitHub repository celigo/ai (3 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 3,797 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
pinecone
Managed vector DB for production RAG and search.
vector-db
Vector database expert for embeddings, similarity search, RAG patterns, and indexing strategies.
redis-expert
Redis expert for data structures, caching patterns, Lua scripting, and cluster operations.
pn-caching
Caching strategies for backend services and frontend apps. Redis patterns (read-through, write-behind, TTL), HTTP cache headers, Next.js fetch caching, Vercel Edge Config, and SWR/React Query. Use when optimising response times or reducing database load.
milvus
Operate Milvus vector database with pymilvus Python SDK. Use when the user wants to connect to Milvus, create collections, insert vectors, perform similarity search, hybrid search, full-text search, manage indexes, partitions, databases, or RBAC via Python code.
caching-strategy
Adds caching to expensive operations - Redis, in-memory, HTTP cache headers.