catalyst-cache
SkillCatalyst Cache — in-memory key-value store with TTL for ephemeral session and temporary data. Trigger on 'Cache', 'cache segment', 'cache key', 'TTL', 'segment.put', 'segment.get', or 'temporary data Catalyst'.
Install
git clone https://github.com/catalystbyzoho/claude-plugin.git ~/.claude/skills/catalyst-cacheWhat is catalyst-cache?
Catalyst Cache — in-memory key-value store with TTL for ephemeral session and temporary data. Trigger on 'Cache', 'cache segment', 'cache key', 'TTL', 'segment.put', 'segment.get', or 'temporary data Catalyst'.
What this can do
Capabilities declared in this component's own frontmatter — not inferred.
Inherit all session tools
Declares no tool restrictions — inherits every session tool
~53 tokens of context used while enabled, before you invoke anything
Documentation
README · ~1 min readHow It Works
Before any MCP call, establish context once per session via the workspace readiness gate:
../catalyst-basics/references/preflight.md. It resolves and reconciles the org/project soCatalystbyZoho_List_All_Segmentstargets the right project.
- Get Segment ID — Use MCP (
CatalystbyZoho_List_All_Segments) if available; otherwise retrieve it from the console or.catalystrc. - Load
references/cache-basics.md— for SDK operations, TTL limits (48 hr max), and thesegment.delete()/segment.update()gotchas. - String values only — All cache values are strings. Always
JSON.stringifybeforeputandJSON.parseafterget. - TTL behavior —
segment.update(key, value)without an expiry argument resets the TTL to 48 hours (the max), not the key's original TTL. Always pass the TTL explicitly (in hours) to preserve it:segment.update(key, value, ttlHours).segment.delete()returnsnull(not an error) if the key is missing.
Triggers
Use this skill for: "Cache", "cache segment", "cache key", "cache value", "TTL", "in-memory store", segment.get, segment.put, segment.delete, "session data", "temporary data Catalyst", "cache vs Data Store", or "48-hour cache".
References
| Reference | Load when the query is about… |
Reviews
Log in to leave a review.
No reviews yet — be the first.
Explore related
Other things in this space — across every part of the ecosystem, not just skills.
Skillssimilar to this one
All skills →ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
235.3K stars
claude-mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
88.9K stars
mem0
Universal memory layer for AI Agents
62K stars
Plugins
All plugins →claude-md-management
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
32.9K stars
beads
Beads - A memory upgrade for your coding agent
25.7K stars
context-mode
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
19.4K stars
MCP Servers
All mcp servers →codebase-memory-mcp
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
36.7K stars
infranodus-mcp-server-infranodus
Map text into knowledge graphs to create a structured representation of conceptual relations and t…
95 stars
sverklo
Local-first MCP code intelligence: 37 tools — hybrid search, blast-radius, diff review, memory.
76 stars
Subagents
All subagents →ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
235.3K stars
maestro-flow
Intent-driven workflow orchestration for multi-agent AI development — adaptive lifecycle engine, self-reinforcing knowledge graph, and visual dashboard for Claude Code, Gemini, Codex & more
486 stars
nimble-analyst
Deep analysis agent for Nimble business skills. Use when a skill needs to synthesize research findings, cross-reference data, produce structured reports, or make strategic assessments. Has persistent memory to learn user preferences and analysis patterns across sessions. Use proactively for any task