Ross ROSS = Recommend OSS · open-source software intelligence for agents

BayramAnnakov/claude-reflect

A self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md. observed · 2026-08-28

github.com/BayramAnnakov/claude-reflect · Python · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

60/100

  • Activity 72
  • Release rhythm 70
  • Longevity 17
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 1.0
  • age_days: 242
  • days_rel: 202
  • days_push: 170
  • n_releases_24m: 13

Full methodology

Adoption not part of the score

1415 stars · 118 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Claude Code plugin that captures user corrections and positive feedback via hooks, then syncs them into CLAUDE.md and AGENTS.md as permanent memory. It also analyzes past session history to discover repeating workflow patterns and suggest reusable slash-command skills.

Use cases

  • make Claude Code remember my corrections across sessions
  • automatically capture feedback I give to Claude Code
  • sync learnings into CLAUDE.md
  • find repeating patterns in my Claude Code sessions
  • generate reusable slash commands from my workflow
  • improve Claude Code skills based on corrections

When to choose

  • you use Claude Code daily and keep repeating the same corrections
  • you want persistent, versioned memory for AI coding assistants
  • you want to turn recurring tasks into reusable commands

When to avoid

  • you don't use Claude Code or similar agent CLIs
  • you prefer manually curating your CLAUDE.md
  • you need a general-purpose LLM memory library outside coding workflows

Facets

plugin · maturity active

agent-framework prompt-engineering developer-tools workflow-automation configuration-management developer-tools artificial-intelligence windows python cli claude-code claude-skills memory self-learning claude-md hooks skill-discovery ai-agents automation macos linux

1 source

Member repositories

RepositoryRoleHealth v2
BayramAnnakov/claude-reflectmain60

For agents

markdown · JSON · MCP: product_card(name="BayramAnnakov/claude-reflect")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem