ejentum-memory

v0.1.0

Cognitive scaffold for sharpening perceptions and observations across multi-turn context. Calls harness_memory on the ejentum MCP server to retrieve a perception scaffold (perception failure, detection procedure, suppression vectors) that sharpens an existing observation. Requires ejentum-mcp and EJENTUM_API_KEY.

Claude Code1 skill

by EjentumMIT2.6kupdated 10 hours ago

Source

$ git clone https://github.com/jeremylongshore/claude-code-plugins-plus-skills

Clone the source, then follow the repository's marketplace instructions for your runtime. The plugin root is plugins/community/ejentum-memory/ inside the repository.

Layout

plugins/community/ejentum-memory/

├── .claude-plugin/plugin.json
└── SKILL.md

Skills1

memorySKILL.md

Use when sharpening a perception or observation you ALREADY formed about conversation state, user behavior, drift, emotional shifts, or cross-turn patterns. Trigger phrases include "what did you notice about X", "the user keeps doing Y", "I sense something has changed", "is the user X-ing", "what does this pattern suggest", "what shifted across our turns", "am I missing something here", "why did the conversation move from X to Y", or any moment requiring verification of whether a felt signal is real or projection. The skill calls the memory MCP tool to retrieve a perception scaffold (perception failure, detection procedure, suppression vectors) that SHARPENS an observation you already have. It is NOT a substitute for observing first. Do NOT trigger for fact extraction, summarization, list-making, factual lookups, or write-heavy memory tasks (storing/retrieving structured data). Memory harness is filter/perception oriented; calling on write-heavy tasks produces scaffold paralysis.

Manifests1

plugins/community/ejentum-memory/.claude-plugin/plugin.json

{
  "name": "ejentum-memory",
  "version": "0.1.0",
  "description": "Cognitive scaffold for sharpening perceptions and observations across multi-turn context. Calls harness_memory on the ejentum MCP server to retrieve a perception scaffold (perception failure, detection procedure, suppression vectors) that sharpens an existing observation. Requires ejentum-mcp and EJENTUM_API_KEY.",
  "author": {
    "name": "Ejentum",
    "url": "https://github.com/ejentum",
    "email": "info@ejentum.com"
  },
  "license": "MIT",
  "repository": "https://github.com/ejentum/ejentum-mcp"
}