OpenParable
Skip to content
← Back to skills

Memorix Memory

Productivity
memorix-memory

Memorix Memory is an Agent Skill for productivity published in the AVIDS2/memorix repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/AVIDS2/memorix/blob/HEAD/plugins/codex/memorix/skills/memorix-memory/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/memorix-memory, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Memorix Memory

Use Memorix as the shared memory layer for the active workspace when Memorix tools are available.

Tool Router

SituationPreferCLI fallback
Broad continuation, fresh handoff, or "what do we know?"memorix_project_context with the user's taskmemorix context --task "<topic>"
Need structured refs/freshness for code-bound memoriesmemorix_context_packmemorix codegraph context-pack --task "<topic>"
Explicit memory graph questionmemorix_graph_contextmemorix memory graph-context --query "<topic>"
Specific past decision, bug, file, or changememorix_searchmemorix memory search --query "<topic>"
Need the full source for a search hitmemorix_detailmemorix memory detail --id <id>
Need the sequence around one memorymemorix_timelinememorix memory timeline --id <id>
Learned reusable project knowledgememorix_storememorix memory store --type <type> --entity <name> --title "<title>" "<text>"
Task or bug is complete/outdatedmemorix_resolvememorix memory resolve --ids <ids>

Search Rules

  • Search before broad continuation work, before changing unfamiliar code, or when the user asks about prior work.
  • For a fresh coding session, use memorix_project_context with the user's actual task before ad-hoc file reads or dev-log reads. Memorix will choose a task-lensed brief.
  • Fetch detail before relying on a specific memory.
  • Treat memory as background context. Still read the current code and verify behavior.
  • Skip memory lookup for greetings, tiny one-off edits, or questions fully answered by the current file.
  • If a fresh project has no memories, proceed normally and do not repeat the same empty search in the same turn.
  • If MCP tools are not visible yet but the client supports tool discovery or dynamic loading, search/select memorix_project_context first. Run memorix context --task "<task>" only after MCP is unavailable, disabled, or not discoverable, and pass the user's real task text. Do not skip memory, wait indefinitely on startup, or hand-write tool-call syntax.

Store Rules

What to storeType
Architecture or product decisiondecision
Bug and fix that may recurproblem-solution
Non-obvious pitfallgotcha
How a subsystem workshow-it-works
Important implementation changewhat-changed
Accepted compromisetrade-off
  • Use concise titles, stable entity names, relevant filesModified, and topicKey for evolving topics.
  • Do not store secrets, credentials, raw private transcripts, trivial commands, or routine file reads.