Skip to main content
mem-recall makes the AI invoke trellis mem whenever the user references past conversations, retrieve content from local Claude Code, Codex, Grok, OpenCode, Pi and ZCode session stores, and answer with session-id + verbatim quotation. Trigger phrases include last time, we discussed, what did I tell <Claude/Codex>, find ... last week, 上次, 之前, and other references to prior dialogue. Without the skill, the AI defaults to “I don’t have that context” or speculative answers. The skill’s frontmatter description field instructs the AI to run trellis mem in these cases, with a search → context two-step retrieval flow.

​
Prerequisites

​
Install

Or install all marketplace skills:
Ask the AI which skills are available; mem-recall should appear in the list.

​
Trigger examples

No manual command needed. The following user messages trigger the skill:
  • last time how did we solve the wait_agent deadlock in #240?
  • which project did I discuss the plugin design in?
  • find what I told Claude about memory architecture last week
  • 上次我们怎么处理 #240 的来着？

​
Retrieval flow

The skill instructs the AI to execute two steps. Step 1 — Candidate search
Multi-token AND search across cleaned dialogue. Returns ranked sessions. Score formula: (3 × user_hits + assistant_hits) / total_turns. User-turn hits are weighted ×3 because user wording reflects topic intent more strongly than AI elaboration. Step 2 — Content extraction
Returns the top-N hit turns plus surrounding context. Default character budget ≤6000, adjustable via --max-chars. trellis mem strips the following before searching, so hits reflect actual dialogue:
  • prompt injections: <system-reminder>, <workflow-state>, <INSTRUCTIONS>, <environment_context>, etc.
  • Codex AGENTS.md preamble (first user message is dropped entirely)
  • tool calls and tool results (only text blocks retained) Turns from before a compaction are kept, with a marker showing where the compaction happened. Content the platform does not store in readable form is reported instead of silently dropped: Codex encrypts messages between agents, and Grok keeps pre-compaction turns as rendered markdown.

​
Data sources

Reads local files directly. No daemon, no index, no upload.

​
Out-of-scope use cases

mem-recall is for AI conversation history only, not file or code search.

​
Performance

Stateless. Each invocation cold-reads from disk; OS page cache absorbs IO so warm and cold runs perform similarly.