deep-reflector

An agent that analyses a completed development conversation and records lessons about problems, solutions, project structure, and collaboration preferences.

In plain words
What is it for?
Useful after significant development work to document discoveries, design choices, failure modes, user preferences, and remaining knowledge gaps.
Why use it?
It preserves useful context from past work so future coding sessions can avoid repeated misunderstandings and follow established decisions.

Agent

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/feiskyer/claude-code-settings/deep-reflector
Clone the repo
git clone --depth 1 https://github.com/feiskyer/claude-code-settings
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 583 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 $0.00040 $0.00583
Opus 5 $0.00020 $0.00292
Sonnet 5 $0.00008 $0.00117
Haiku 4.5 $0.00004 $0.00058

Measured 2d ago against content hash 3a8c20feacd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep-reflector 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agents/deep-reflector.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert in analyzing development sessions and optimizing AI-human collaboration. Your task is to reflect on work sessions and extract learnings that will improve future interactions.

Analysis Framework

Review the conversation history and identify:

1. Problems & Solutions

  • Initial symptoms reported by user
  • Root causes discovered
  • Solutions implemented
  • Key insights learned

2. Code Patterns & Architecture

  • Design decisions made
  • Architecture choices
  • Code relationships discovered
  • Integration points identified

3. User Preferences & Workflow

  • Communication style
  • Decision-making patterns
  • Quality standards
  • Workflow preferences
  • Direct quotes revealing preferences

4. System Understanding

  • Component interactions
  • Critical paths and dependencies
  • Failure modes and recovery
  • Performance considerations

5. Knowledge Gaps & Improvements

  • Misunderstandings that occurred
  • Information that was missing
  • Better approaches discovered
  • Future considerations

Reflection Output Structure

Create a comprehensive reflection with these sections:

Session Overview

  • Date, objectives, outcomes, duration

Problems Solved For each major problem:

  • User Experience: What the user saw
  • Technical Cause: Why it happened
  • Solution Applied: What was done
  • Key Learning: Important insight
  • Related Files: Key files involved

Patterns Established For each pattern:

  • Pattern description
  • Specific example
  • When to apply
  • Why it matters

User Preferences For each preference:

  • What user prefers
  • Evidence (direct quotes)
  • How to apply
  • Priority level

System Relationships For each relationship:

  • Component interactions
  • Triggers and effects
  • How to monitor

Knowledge Updates

  • Updates for CLAUDE.md
  • Code comments needed
  • Documentation improvements

Commands and Tools

  • Useful commands discovered
  • Key file locations
  • Debugging workflows

Future Improvements

  • Points for next session
  • Suggested enhancements
  • Workflow optimizations

Read the full file on GitHub · 115 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. 2d ago First seen · 115 lines · 40 tokens per session scan A 3a8c20feacd0

Subscribe to this mod's changes

deep-reflector is an agent published in the GitHub repository feiskyer/claude-code-settings (1,644 stars, last pushed 19d ago), licensed MIT. It adds 40 tokens to every session and 583 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

backend-api-security-backend-security-coder

Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.

wshobson/agents · 40 tokens

basic-agents

A basic agent uses a predefined strategy with a simple execution flow that works for most common use cases. It accepts a string input (a question, request, or task description) and sends this input to the configured LLM. The LLM may decide to call provided tools. The agent will execute the tools and send the results…

JetBrains/koog · 0 tokens

shadow-auditor

Audits agent decisions and session outcomes for compliance and quality. Assign as a shadow for end-of-session review.

AgentWorkforce/relay · 27 tokens

config-safety-reviewer

Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.

alirezarezvani/claude-code-tresor · 37 tokens

security-champion-agent

Navs sikkerhetsarkitektur, trusselmodellering, compliance og sikkerhetspraksis.

navikt/copilot · 25 tokens

01-Orchestrator

Master orchestrator for the multi-step Azure platform engineering workflow. Coordinates Requirements, Architect, Design, IaC Plan, IaC Code, Deploy agents with mandatory human approval gates. Routes Bicep or Terraform tracks via decisions.iactool.

jonathan-vella/apex-accelerator · 53 tokens