agentmods.dev

echo-sleuth-for-claude: Instructions file for Claude Code

CLAUDE.md

echo-sleuth-for-claude CLAUDE.md is an instructions file for Claude Code from xiaolai/echo-sleuth-for-claude. It costs 1,105 tokens per session, scanned A, original, ISC.

Development instructions for Echo Sleuth, a plugin that reads Claude Code's saved conversation files to find past work, decisions, mistakes, and file history. JSONL is a text format that stores one JSON record per line.

In plain words
What is it for?
Use them when working on commands such as recalling or summarizing sessions, building timelines, extracting lessons, auditing stored memories, or cleaning them up.
Why use it?
They explain how the plugin's commands, agents, reusable knowledge, and parsing scripts fit together, making changes easier to place and test.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions Claude Code.

This is xiaolai/echo-sleuth-for-claude's own configuration. It tells Claude Code how to work on echo-sleuth-for-claude itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything echo-sleuth-for-claude configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

not rated 9repo 14d ago A scan 1,105 tokens original ISC
View source ↗ xiaolai/echo-sleuth-for-claude
Reuse

Borrowing it

Nothing to install: this file belongs to xiaolai/echo-sleuth-for-claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/xiaolai/echo-sleuth-for-claude/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/xiaolai/echo-sleuth-for-claude

Made for: Claude Code.

Wrote 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.

agentmods badge for echo-sleuth-for-claude CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xiaolai/echo-sleuth-for-claude/claude-md.svg)](https://agentmods.dev/instructions/xiaolai/echo-sleuth-for-claude/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/xiaolai/echo-sleuth-for-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/xiaolai/echo-sleuth-for-claude/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,105 This file is loaded in full into every session.
When invoked 1,105 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01105 $0.01105
Opus 5 $0.00553 $0.00553
Sonnet 5 $0.00221 $0.00221
Haiku 4.5 $0.00111 $0.00111

Measured 8d ago against content hash 916cd4081dde, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

echo-sleuth-for-claude CLAUDE.md scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- curl (optional, needed only for URL validation in /audit --deep)
CLAUDE.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Echo Sleuth — Plugin Development Guide

Purpose

Echo Sleuth mines Claude Code session JSONL files for insights. It helps users recall past work, trace decisions, learn from mistakes, and understand file histories by analyzing ~/.claude/projects/ conversation data.

Architecture

commands/  → User-facing slash commands (entry points)
agents/    → Task-specific agents dispatched by commands via the Task tool
skills/    → Reusable knowledge (parsing rules, git patterns, synthesis taxonomy)
scripts/   → Python/bash tools that do the actual JSONL parsing and extraction

Flow: Commands dispatch to agents. Agents use skills for domain knowledge and call scripts (via Bash tool) for data extraction. Scripts are thin bash wrappers around scripts/echolib.py.

Commands

  • /recall — Search and analyze past sessions
  • /recap — Summarize recent sessions
  • /timeline — Chronological project history (sessions + git)
  • /lessons — Extract lessons learned
  • /dashboard — Global memory overview and staleness alerts
  • /audit — Memory staleness audit (heuristic or deep)
  • /extract — Extract knowledge from conversation sessions
  • /prune — Interactive memory cleanup

Agents

  • recall — Unified search: session finding, decision archaeology, mistake hunting
  • file-historian — Trace a file's history across sessions and git
  • analyze — Deep analysis of specific sessions
  • schema-scout — Detect JSONL schema changes
  • memory-auditor — Deep content-aware memory verification

Skills

  • jsonl-core — Canonical JSONL parsing infrastructure and record type reference
  • git-mining — Git log/blame/diff patterns for correlating commits with sessions
  • experience-synthesis — Taxonomy for categorizing insights (decisions, mistakes, patterns)
  • memory-management — Memory format, staleness scoring, and routing knowledge

Scripts

All in scripts/, require only Python 3.6+ (stdlib only) and bash. Git scripts additionally require git.

  • echolib.py — Core Python parsing module (no pip dependencies)
  • list-sessions.sh — Index-based session listing with grep/limit
  • session-stats.sh — Single-pass session statistics
  • extract-messages.sh — Human-readable message extraction
  • extract-tools.sh — Tool call extraction with error filtering
  • extract-files-changed.sh — Files edited in a session
  • parse-jsonl.sh — Low-level JSONL parser with schema detection
  • build-index.sh — Build fallback index for projects without sessions-index.json
  • git-context.sh / git-sessions.sh — Git history helpers
  • memory-dashboard.sh — Memory overview and heuristic audit output
  • extract-knowledge.sh — Two-pass knowledge extraction from sessions
  • recall-lite.sh — End-to-end no-API recall: list-sessions + extract-messages + extract-tools, dumped raw. Wraps the others. Invoked by /recall --lite and runnable directly from a shell.

Read the full file on GitHub · 72 lines

Changes

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.

  1. 8d ago First seen · 72 lines · 1,105 tokens per session scan A 916cd4081dde

Subscribe to this mod's changes

echo-sleuth-for-claude CLAUDE.md is an instructions file published in the GitHub repository xiaolai/echo-sleuth-for-claude (9 stars, last pushed 14d ago), licensed ISC. It adds 1,105 tokens to every session, about $0.0055 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsMemory and context
Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens