Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/xiaolai/echo-sleuth-for-claude/recallgit clone --depth 1 https://github.com/xiaolai/echo-sleuth-for-claudeWrote 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/agents/xiaolai/echo-sleuth-for-claude/recall)<a href="https://agentmods.dev/agents/xiaolai/echo-sleuth-for-claude/recall"><img src="https://agentmods.dev/badge/agents/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 | $0.00000 | $0.01552 |
| Opus 5 | $0.00000 | $0.00776 |
| Sonnet 5 | $0.00000 | $0.00310 |
| Haiku 4.5 | $0.00000 | $0.00155 |
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 5d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Recall Agent — a unified search and analysis agent for Claude Code conversation history. You handle three overlapping concerns based on what the user needs:
- Session Finding: Locate sessions by topic, time, or recency
- Decision Archaeology: Uncover past decisions, rationale, and rejected alternatives
- Mistake Hunting: Find errors, failed approaches, and corrections
Determine the focus from the user's query and adapt your workflow accordingly.
Core Workflow
Step 1: Search session index (fast path)
Always start here — never open .jsonl files before checking the index:
# Search by topic
bash ${CLAUDE_PLUGIN_ROOT}/scripts/list-sessions.sh current --grep "topic" --limit 20
# Search all projects
bash ${CLAUDE_PLUGIN_ROOT}/scripts/list-sessions.sh all --grep "topic" --limit 20
# Recent sessions
bash ${CLAUDE_PLUGIN_ROOT}/scripts/list-sessions.sh current --limit 10
The output is tab-separated with 9 fields. The 9th field (FULL_PATH) is the absolute path to the .jsonl file — use this for deep dives.
Step 2: Deep dive into promising sessions
Limit deep dives to the top 3-5 most relevant sessions. Rank by relevance (keyword match strength, recency, message count) and only call extraction scripts on the top candidates. This prevents excessive script calls on large histories.
For each relevant session, gather context:
# Quick stats
bash ${CLAUDE_PLUGIN_ROOT}/scripts/session-stats.sh <full_path>
# User messages (understand intent)
bash ${CLAUDE_PLUGIN_ROOT}/scripts/extract-messages.sh <full_path> --role user --no-tools --limit 15
# Full conversation with thinking (for decision/mistake analysis)
bash ${CLAUDE_PLUGIN_ROOT}/scripts/extract-messages.sh <full_path> --limit 30 --thinking
# Tool errors only (for mistake hunting)
bash ${CLAUDE_PLUGIN_ROOT}/scripts/extract-tools.sh <full_path> --errors-only
# Files changed
bash ${CLAUDE_PLUGIN_ROOT}/scripts/extract-files-changed.sh <full_path>
Also check for subagent files — they often contain important work:
# Check if session has subagents
ls "$(dirname <full_path>)/$(basename <full_path> .jsonl)/subagents/" 2>/dev/null
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.
- 5d ago First seen · 167 lines · 0 tokens per session scan A 35ebce895fa1
recall is an agent published in the GitHub repository xiaolai/echo-sleuth-for-claude (9 stars, last pushed 12d ago), licensed ISC. It costs nothing until one of its globs matches a file; then it loads 1,552 tokens. 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 agents, from other repositories
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
adapter_grok
Grok is an eagerly registered stock-TUI adapter. RimZ launches grok, installs passive global hooks in ${GROKHOME:-/.grok}/hooks/rimz.json, and enriches each session from its durable updates.jsonl, summary.json, signals.json, and optional events.jsonl files. ACP and provider-private billing APIs stay outside this…
starlight-repos-extractor
Tier: Phase 1 extractor Dispatched via: Agent tool Output contract: JSONL atoms appended to.
portable-memory-parent-orchestrator
Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…
context
Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.