# Cross Agent Recall

> Recall the user's past coding-agent sessions across Claude Code AND Codex via uni-code. Use when the user references earlier work, a past fix, a decision, a command they ran before, or a session in another agent ("how did we fix X", "what did I try in Codex yesterday", "the approach from last week").

- Skill: `lum1104/cross-agent-recall` (Agent Skill)
- Install (CLI): `npx skillmds@latest add lum1104/cross-agent-recall`
- Raw SKILL.md: https://api.skillmd.com/api/skills/lum1104/cross-agent-recall/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: Lum1104 (https://skillmd.com/u/lum1104)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/lum1104/cross-agent-recall

---


# Cross-agent recall

This machine has uni-code installed: a local, read-only index of every Claude Code and Codex session, exposed through the `uni-code` MCP server.

## When to reach for it

- The user references past work you don't have in context: "that bug we fixed", "the command from last time", "why did we choose X".
- The user mentions another agent: "I started this in Codex", "Claude tried something yesterday".
- You are about to re-derive something (a config, a fix, an investigation) the user has plausibly done before — one cheap search first can save the whole rework.

## How to use it

1. `resume_session` when the user wants to CONTINUE earlier work in earnest ("resume the Codex session", "continue exactly where I left off") — it reconstructs the session's effective context: the source agent's own compaction summary plus everything after it. Pass `project: "."`; if the result turns out to be this very conversation, pass the other agent's name or an explicit id.
2. `get_handoff` for a quick one-page orientation instead (goal, where it ended, files touched, commands, errors) when the user just wants you up to speed, not a full continuation.
3. `search_history` with distinctive terms — code identifiers and error strings beat prose; Chinese/Japanese/Korean queries work. Add `project: "."` to scope to the current project.
4. `read_session` on the best hit's id. Default returns the END of the session (outcomes, conclusions); pass `from_start: true` to see the original goal.
5. `list_sessions` when there is no search term — e.g. "what was I doing yesterday?".

## Notes

- Results may come from a different agent than the current one; treat them as the user's own history, and say which agent/session an answer came from.
- Everything is local and read-only; the index refreshes automatically on each query. If the very first query on a machine is slow, that is the one-time initial indexing.
- If a search returns nothing, retry once with fewer or different terms before concluding the history doesn't exist.