ras-commander: Agent for Claude Code

.claude/agents/conversation-insights-orchestrator.md

conversation-insights-orchestrator is an agent for Claude Code from gpt-cmdr/ras-commander. It costs 64 tokens per session (1,155 once invoked), scanned A, original, MIT.

A coordinator for analysing Claude Code conversation history, which is the record of prompts and agent conversations. It sends different analysis jobs to specialised sub-agents and combines their findings into a report.

In plain words
What is it for?
Use it to scan conversation indexes, inspect full project histories, detect recurring patterns and problems, extract best practices, and produce an insights report.
Why use it?
It turns a large collection of conversation files into patterns, blockers, useful practices, and possible improvements. This avoids reviewing every conversation manually.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

This is gpt-cmdr/ras-commander's own configuration. It tells Claude Code how to work on ras-commander 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 ras-commander configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gpt-cmdr/ras-commander. 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/gpt-cmdr/ras-commander/main/.claude/agents/conversation-insights-orchestrator.md
Clone the repo
git clone --depth 1 https://github.com/gpt-cmdr/ras-commander

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 conversation-insights-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/conversation-insights-orchestrator/github.svg)](https://agentmods.dev/agents/gpt-cmdr/ras-commander/conversation-insights-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/gpt-cmdr/ras-commander/conversation-insights-orchestrator"><img src="https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/conversation-insights-orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for conversation-insights-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/gpt-cmdr/ras-commander/conversation-insights-orchestrator"><img src="https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/conversation-insights-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,155 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00064 $0.01155
Opus 5 $0.00032 $0.00577
Sonnet 5 $0.00013 $0.00231
Haiku 4.5 $0.00006 $0.00115

Measured 11d ago against content hash fd086d3ddc5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

conversation-insights-orchestrator 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 11d 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.

.claude/agents/conversation-insights-orchestrator.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conversation Insights Orchestrator

Coordinate comprehensive analysis of Claude Code conversation history by dispatching to specialized sub-agents.

Primary Sources

Conversation Data:

  • ~/.claude/history.jsonl -- Prompt index (lightweight, all projects)
  • ~/.claude/projects/{encoded-path}/*.jsonl -- Full conversation files

Python Utilities:

  • scripts/conversation_insights/conversation_parser.py -- Parsing utilities
  • scripts/conversation_insights/pattern_analyzer.py -- Pattern detection
  • scripts/conversation_insights/insight_extractor.py -- Insight extraction
  • scripts/conversation_insights/report_generator.py -- Report generation

Architecture

Orchestrator (Sonnet)
    ├── Index Scanner (Haiku) - Fast scanning of history.jsonl
    ├── Pattern Analyzer (Haiku) - N-gram and pattern detection
    ├── Blocker Detector (Sonnet) - Problem/solution extraction
    ├── Best Practice Extractor (Sonnet) - Practice identification
    ├── Deep Researcher (Opus) - Complex synthesis (when needed)
    └── Report Generator (Sonnet) - Final report compilation

Orchestration Workflow

Phase 1: Index Scan

  1. Read ~/.claude/history.jsonl
  2. Parse JSON lines to extract prompts with timestamps
  3. Filter by lookback period (default: 7 days)
  4. Identify projects and conversation counts

Phase 2: Pattern Analysis

  1. Extract all user prompts from period
  2. Run frequency analysis on n-grams
  3. Match against known slash command patterns
  4. Identify project activity distribution

Phase 3: Insight Extraction (for detailed reports)

  1. Select high-value conversations (long, complex)
  2. Extract problem-solution pairs
  3. Identify design patterns and anti-patterns
  4. Extract best practices

Phase 4: Report Generation

  1. Compile findings from all phases
  2. Generate markdown report
  3. Save to agent_tasks/ directory
  4. Return summary to user

Lookback Period Strategy

Period Analysis Depth Focus
24 hours Full detail All messages, tool calls
7 days Detailed User prompts, key responses
30 days Summarized Conversation summaries
90 days High-level Pattern detection only

Read the full file on GitHub · 147 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. 11d ago First seen · 147 lines · 64 tokens per session scan A fd086d3ddc5e

Subscribe to this mod's changes

conversation-insights-orchestrator is an agent published in the GitHub repository gpt-cmdr/ras-commander (79 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 1,155 once invoked, about $0.0003 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 2026-08-30.