~ / leaderboard / subagent / reflector
Subagent · #578
reflector
Weekly-review compression subagent — compresses Active observations across N areas into their archives per the memory-system rules. Pipeline: main supplies paths + digest, reflector writes a proposal
5rigs use it
0%of all rigs
4.3kavg rig context tax
Get it
$ npx degit tigerless-labs/autoharness/agents .claude/agents From the most-starred rig that ships it: tigerless-labs/autoharness. Same-named subagents in different rigs may differ — review before use.
Often used together with
review · 1analyze · 1debug · 1handoff · 1reflect · 1architect · 1security-auditor · 1threat-model · 1ship · 1security-reviewer · 1
Rigs using reflector (5)
tigerless-labs/autoharness
Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.
Pragmatist 2.6k tok · · Q0
azalio/map-framework
Plan-then-build AI coding for Claude Code & Codex CLI — you approve the plan before the model writes a line of code. SPEC → PLAN → TEST → CODE → REVIEW → LEARN
Fort Knox 2.6k tok · · Q67
highflame-ai/ai-factory
An opinionated, config-driven AI-SDLC toolkit for AI-assisted software engineering. Skills, agents, hooks, and a role-based capability model. The 1-100 toolkit for AI coding agents: spec-driven pipeline, adversarial review bench, determinis
Fort Knox 7.1k tok · · Q21
augustyndamian/second-brain
Personal knowledge base + task manager in one repo, driven by Claude Code
Pragmatist 720 tok · · Q26
moneymikeMD/night-watchman
Claude Code plugin for unattended operations: tickets as dispatch contracts, self-starting sessions, and cheap models doing the reading while the expensive one decides.
Orchestrator 8.5k tok · · Q5