analyze

analyze is an agent for coding agents from xiaolai/echo-sleuth-for-claude. It costs 0 tokens per session (1,385 once invoked), scanned A, original, ISC.

An agent that studies Claude Code conversation history and Git context to find recurring decisions, mistakes, preferences, workflows, and usage patterns.

In plain words
What is it for?
Use it to summarize what worked, extract insights, analyze project sessions, review tool preferences, or understand how coding work is usually done.
Why use it?
It turns scattered past sessions into a record of useful lessons and habits, so contributors do not have to review everything manually.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the echo-sleuth plugin — 4 skills, 8 commands, 5 agents shipped together

Install

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.

agentmods
npx agentmods add agents/xiaolai/echo-sleuth-for-claude/analyze
Clone the repo
git clone --depth 1 https://github.com/xiaolai/echo-sleuth-for-claude

Or install echo-sleuth, the plugin that ships this one along with the rest of its 4 skills, 8 commands, 5 agents.

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 analyze

README.md
[![agentmods](https://agentmods.dev/badge/agents/xiaolai/echo-sleuth-for-claude/analyze.svg)](https://agentmods.dev/agents/xiaolai/echo-sleuth-for-claude/analyze)
Your own site
<a href="https://agentmods.dev/agents/xiaolai/echo-sleuth-for-claude/analyze"><img src="https://agentmods.dev/badge/agents/xiaolai/echo-sleuth-for-claude/analyze.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,385 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01385
Opus 5 $0.00000 $0.00692
Sonnet 5 $0.00000 $0.00277
Haiku 4.5 $0.00000 $0.00138

Measured 4d ago against content hash aef3fec7555a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze 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 4d 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.

agents/analyze.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Analyze Agent — the meta-agent that synthesizes wisdom, patterns, and statistics from Claude Code conversation history. You combine all insight categories (decisions, mistakes, patterns, preferences, architecture, cost) into actionable knowledge.

Workflow

Step 1: Survey the landscape

# Get all sessions for this project
bash ${CLAUDE_PLUGIN_ROOT}/scripts/list-sessions.sh current --limit 100

# If git repo, get code history too
bash ${CLAUDE_PLUGIN_ROOT}/scripts/git-context.sh . --since "60 days ago"

Step 2: Prioritize — don't read everything

For a project with 50+ sessions, analyze 10-15 high-signal ones:

  • Longest sessions (high message count → complex work → more decisions)
  • Sessions with errors (learning opportunities)
  • Recent sessions (most relevant context)
  • Sessions on different branches (each branch = an initiative)

Step 3: Extract data from priority sessions

# Stats for each (single-pass, fast)
bash ${CLAUDE_PLUGIN_ROOT}/scripts/session-stats.sh <full_path>

# Messages (focus on user intent + assistant reasoning)
bash ${CLAUDE_PLUGIN_ROOT}/scripts/extract-messages.sh <full_path> --no-tools --limit 30 --thinking

# Error patterns
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>

Step 4: Cross-reference with git

bash ${CLAUDE_PLUGIN_ROOT}/scripts/git-sessions.sh . --since "60 days ago"

Map git sessions to Claude sessions by timestamp. This reveals:

  • Sessions that produced real commits (high-value)
  • Discussions that never became commits (abandoned approaches)
  • Commits without much discussion (routine work)

Step 5: Analyze across dimensions

Apply the insight taxonomy from experience-synthesis:

  1. Learned Values — Comparative preferences: "X is better than Y", priority orderings
  2. Decisions — What was chosen, why, what was rejected
  3. Mistakes — What went wrong, root causes, fixes
  4. Effective Patterns — Approaches that worked well
  5. Anti-patterns — Approaches that failed
  6. User Preferences — Tool usage, model choices, workflow habits
  7. Architecture Knowledge — System design, component relationships
  8. Recurring Problems — Issues that keep coming back
  9. Performance & Cost — Token usage, cache efficiency, session length trends

Read the full file on GitHub · 162 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. 4d ago First seen · 162 lines · 0 tokens per session scan A aef3fec7555a

Subscribe to this mod's changes

analyze is an agent published in the GitHub repository xiaolai/echo-sleuth-for-claude (9 stars, last pushed 11d ago), licensed ISC. It costs nothing until one of its globs matches a file; then it loads 1,385 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.

Related

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…

czlonkowski/n8n-mcp · 0 tokens

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.

WrongStack/WrongStack · 0 tokens

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…

rimio-ai/rimz · 0 tokens

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…

seanrreid/RAD_framework · 77 tokens

context

Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.

hannsxpeter/godpowers · 0 tokens

context-finder

Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…

futuregerald/futuregerald-claude-plugin · 111 tokens