Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add xiaolai/echo-sleuth-for-claude/plugin install echo-sleuthWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/xiaolai/echo-sleuth-for-claude/recall)<a href="https://agentmods.dev/commands/xiaolai/echo-sleuth-for-claude/recall"><img src="https://agentmods.dev/badge/commands/xiaolai/echo-sleuth-for-claude/recall.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.00686 |
| Opus 5 | $0.00017 | $0.00343 |
| Sonnet 5 | $0.00007 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
recall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search past Claude Code conversation sessions for information about: $ARGUMENTS
If no search topic is provided, show the 10 most recent sessions for the current project as a summary list.
Mode selection
Inspect $ARGUMENTS for --lite:
- If
--liteis present → run lite mode below. Do not launch the recall agent. Do not synthesize. - Otherwise → run full mode (the agent path).
Lite mode (--lite)
The user has explicitly opted out of model synthesis. Goals: minimum tokens, raw evidence, no extra reasoning.
- Strip
--litefrom $ARGUMENTS. Pass the remaining arguments to the shell script. - Run the script via the Bash tool. Use the most distinctive keyword from the user's query as the positional argument; pass
--scopeand--limitthrough if present.
bash ${CLAUDE_PLUGIN_ROOT}/scripts/recall-lite.sh <keyword> [--scope ...] [--limit ...]
- Return the script's stdout to the user verbatim, wrapped in a single sentence at the top: "Lite mode — raw matches, no synthesis." Do not summarize, rank, interpret, or add commentary. The user is asking for the raw dump on purpose.
If the user's query is a question (e.g. "how did I import vitepress books"), pick the most distinctive content word as the keyword (e.g. vitepress). State your keyword choice in one line so the user can re-run with a different word if they want.
Full mode (default)
Launch the recall agent via the Task tool with the following context:
- Search topic: $ARGUMENTS
- Current project: the current working directory
- Default scope: "current" project (use "all" if
--scope allis specified) - Default limit: 10 sessions
The recall agent will:
- Search session indices (including fallback index for unindexed projects)
- Deep-dive into the most relevant sessions
- Determine focus from the query (session search, decision archaeology, or mistake hunting)
- Present findings with dates, context, and excerpts
If the query mentions decisions, rationale, "why did we", or alternatives — focus on decision archaeology. If the query mentions errors, mistakes, failures, "what went wrong" — focus on mistake hunting. Otherwise, perform a general session search and summarize findings.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 55 lines · 35 tokens per session scan A 13f050ddb699
recall is a command published in the GitHub repository xiaolai/echo-sleuth-for-claude (9 stars, last pushed 13d ago), licensed ISC. It adds 35 tokens to every session and 686 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.