# Session Recall

> Find prior local Codex or Claude agent sessions with the agent-session-find CLI. Use when context may exist in previous sessions, after compaction or handoff, before asking the user to remember prior work, when searching for old fixes, decisions, commands, errors, file paths, repo context, review outcomes, or "where did we handle this before?" Keep session contents local and use low-token search…

- **Type:** Skill
- **Install:** `agentstack add skill-jesse-merhi-skills-session-recall`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [jesse-merhi](https://agentstack.voostack.com/s/jesse-merhi)
- **Installs:** 0
- **Category:** [Search](https://agentstack.voostack.com/c/search)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [jesse-merhi](https://github.com/jesse-merhi)
- **Source:** https://github.com/jesse-merhi/skills/tree/main/skills/session-recall

## Install

```sh
agentstack add skill-jesse-merhi-skills-session-recall
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Session Recall

Use `agent-session-find` as the first recall step when previous agent work may
answer the current question. The goal is to recover the right full session with
minimal tokens, not to dump transcripts into context.

Keep session contents local. Do not upload session contents or paste whole
session logs into external tools.

## Workflow

1. Confirm the command setup in [command-setup.md](references/command-setup.md).
2. Start with a recent, bounded fuzzy query:
   `agent-session-find --index-since 14d --max-sources 80 ""`.
3. Add repo or cwd context when the project is known:
   `agent-session-find --cwd "" --since 30d ""`.
4. Search one source when the likely harness is known:
   `agent-session-find --source codex ""` or
   `agent-session-find --source claude ""`.
5. If the user mentions a handoff, worker, subagent, delegated implementation,
   reviewer pass, branch, commit, or PR opened by another agent, retry with
   `--workers`.
6. If nothing matches, widen gradually: increase `--index-since`, remove
   `--cwd`, try synonyms, then omit `--max-sources` for a fuller local refresh.
7. If running several follow-up searches against the same index, add
   `--no-refresh` after the first successful refresh.
8. Use [query-strategy.md](references/query-strategy.md) for search terms.
9. Inspect low-token result cards first, then use
   [result-handling.md](references/result-handling.md) before opening logs.

## Defaults

Use these defaults unless the task suggests otherwise:

```sh
agent-session-find --index-since 14d --max-sources 80 ""
agent-session-find --cwd "" --since 30d ""
agent-session-find --limit 5 ""
```

For stale or long-running projects, prefer `--index-since 90d` over an
unbounded first pass. Run `agent-session-find status` when you need to see index
size before widening.

## Context Pointers

- Use [command-setup.md](references/command-setup.md) for binary, wrapper,
  privacy, database, and parallel-refresh rules.
- Use [query-strategy.md](references/query-strategy.md) for query terms and
  widening strategy.
- Use [result-handling.md](references/result-handling.md) for interpreting
  result cards and deciding when to open local JSONL.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [jesse-merhi](https://github.com/jesse-merhi)
- **Source:** [jesse-merhi/skills](https://github.com/jesse-merhi/skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-jesse-merhi-skills-session-recall
- Seller: https://agentstack.voostack.com/s/jesse-merhi
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.