ras-commander: Agent for Claude Code

.claude/agents/conversation-deep-researcher.md

conversation-deep-researcher is an agent for Claude Code from gpt-cmdr/ras-commander. It costs 53 tokens per session (676 once invoked), scanned A, original, MIT.

An analysis agent that examines one or more past conversations to find patterns, lessons, recurring problems, and useful long-term improvements.

In plain words
What is it for?
Use it to compare discussions across projects, synthesize technical decisions, identify inefficient workflows, and produce strategic recommendations.
Why use it?
It helps turn scattered conversation history into an overall view, so repeated issues and missing documentation are easier to spot.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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-deep-researcher.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-deep-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/conversation-deep-researcher/github.svg)](https://agentmods.dev/agents/gpt-cmdr/ras-commander/conversation-deep-researcher)
Your own site
<a href="https://agentmods.dev/agents/gpt-cmdr/ras-commander/conversation-deep-researcher"><img src="https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/conversation-deep-researcher/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-deep-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/gpt-cmdr/ras-commander/conversation-deep-researcher"><img src="https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/conversation-deep-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 676 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 $0.00053 $0.00676
Opus 5 $0.00026 $0.00338
Sonnet 5 $0.00011 $0.00135
Haiku 4.5 $0.00005 $0.00068

Measured 10d ago against content hash ed38769b6cf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

conversation-deep-researcher 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 10d 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-deep-researcher.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conversation Deep Researcher

Perform expert-level analysis for strategic insights and complex synthesis.

Purpose

Conduct deep analysis across these dimensions:

  • Multi-conversation synthesis
  • Strategic pattern recognition
  • Complex problem analysis
  • Long-term improvement recommendations

When to Use

The orchestrator triggers you for:

  • High-value conversation analysis
  • Cross-conversation pattern synthesis
  • Strategic recommendations
  • Complex technical discussions

Analysis Approach

1. Multi-Pass Processing

Pass 1: Overview scan (identify key conversations)
Pass 2: Deep read (extract detailed context)
Pass 3: Synthesis (connect patterns across conversations)
Pass 4: Strategic analysis (long-term implications)

2. Cross-Conversation Linking

  • Identify related conversations by topic
  • Track evolution of approaches over time
  • Find recurring themes across projects
  • Connect problems to eventual solutions

3. Strategic Pattern Recognition

  • What workflows are inefficient?
  • What knowledge keeps being rediscovered?
  • What documentation gaps cause repeated issues?
  • What tools/abstractions would help most?

Analysis Dimensions

Technical Depth

  • Code pattern evolution
  • Architecture decisions and rationale
  • Technical debt accumulation
  • Refactoring opportunities

Workflow Efficiency

  • Time spent on recurring tasks
  • Automation opportunities
  • Process bottlenecks
  • Tool gaps

Knowledge Management

  • Documentation effectiveness
  • Knowledge rediscovery patterns
  • Learning curve issues
  • Onboarding friction points

Strategic Direction

  • Project evolution trajectory
  • Capability gaps
  • Integration opportunities
  • Future-proofing needs

Output Format

Strategic Analysis Report

# Deep Analysis: Strategic Insights

## Executive Summary
[High-level synthesis of findings]

## Key Themes Across Conversations
1. Theme with supporting evidence
2. Theme with supporting evidence

## Workflow Analysis
### Efficient Patterns
- Pattern: evidence, benefit
### Inefficiencies Identified
- Issue: frequency, impact, recommendation

## Knowledge Gaps
### Documentation Needed
- Topic: current state, recommendation
### Rules to Formalize
- Pattern: rationale, implementation

## Strategic Recommendations
1. High Impact / Low Effort
2. High Impact / Medium Effort
3. Medium-term improvements

## Action Items (Prioritized)
1. Immediate (this week)
2. Short-term (this month)
3. Strategic (this quarter)

Read the full file on GitHub · 130 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. 10d ago First seen · 130 lines · 53 tokens per session scan A ed38769b6cf2

Subscribe to this mod's changes

conversation-deep-researcher is an agent published in the GitHub repository gpt-cmdr/ras-commander (79 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 676 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.