claude

reflection

Passively watches every session for moments the agent didn't meet expectations, logs them, nudges /reflecting at session start, and synthesizes root-cause-attributed improvement reports

2 on GitHubby TOA5TERv0.10.0MITupdated 13 days ago
/

Plugin reflection from marketplace claude-quest in TOA5TER/claude-quest. Commands read from the repo's manifest — 13 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (1)

  • reflection:reflecting

    Use when the user wants to review what went wrong in recent sessions, asks why the agent keeps getting corrected on the same thing, or says '/reflecting', 'review how this session went,' or 'what problems came up.'

Hooks (2)

  • SessionStart

    uv run ${CLAUDE_PLUGIN_ROOT}/hooks/reflection_session_start.py --mode=instructions

  • SessionStart

    uv run ${CLAUDE_PLUGIN_ROOT}/hooks/reflection_session_start.py --mode=nudge

View source on GitHub

More from TOA5TER/claude-quest

All 10 plugins →

Role-based development workflow subagents with pluggable PM and notes adapters (requires guardrails-git >= 1.2.0 for worktree support)

10 skills · 5 agents · hooks

2

Self-hosted, zero-dependency dashboard server that tracks which coding-agent sessions are waiting on you

hooks

2

Logs every Claude Code tool call (input and output) to JSON files in ~/.claude/logs/ for auditability and debugging

hooks

2

Skills and utilities for maintaining and integrating with the claude-quest plugin marketplace

1 skill

2

Bash and shell safety guards: blocks rm -rf, /tmp usage, cat/echo file writes, cd outside repo, and unsafe gradle commands

hooks

2

Docker safety guards: enforces timeout on docker build commands

hooks

2

Similar plugins

ecc

claudecodex

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

affaan-m/ECC 302,088

Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.

7 skills · 1 command · 3 agents

anthropics/claude-code 155,476

CMEM Pro

claude

CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents

3 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.

1 skill

headroomlabs-ai/headroom 79,508

mempalace

claudecodex

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks

MemPalace/mempalace 60,536

Maintain reflection?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins10 plugins