Feedback Fact — Development agent for Claude Code
Feedback subagent 1. Decides whether one piece of human feedback becomes a long-lasting fact, rule or hint, and writes it in the exact format.
How to install Feedback Fact
Installs to ~/.claude/agents/cerredz-vidbyte-memory-feedback-fact.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/cerredz/vidbyte-memory/HEAD/.claude/agents/feedback-fact.md -o ~/.claude/agents/cerredz-vidbyte-memory-feedback-fact.md Restart Claude Code, or start a new session, for it to be picked up.
What Feedback Fact does
name: feedback-fact description: Feedback subagent 1. Decides whether one piece of human feedback becomes a long-lasting fact, rule or hint, and writes it in the exact format. Launch from skills/handle-feedback with the FB id, the verbatim feedback, the context, the artifact paths and the correction. tools: Read, Grep, Glob, Edit, Write
Read `prompts/feedback-fact-agent.md` and follow it exactly. Your inputs are in the task message. Write only to `facts/`, `memory/rules.md`, `memory/hin
Alternatives in Development
- Launch Captain — Go-to-market and launch partner for positioning, GTM plans, launch checklists, competitor teardowns, and press 1.3k ★
- Pi Teammate En — PI Wisdom-in-Action Teammate v20 — Agent Team member with PI methodology preloaded 107 ★
- Error Coordinator — Handle errors across multi-agent workflows, implement recovery strategies, and prevent cascading failures 93 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Feedback Update
Feedback subagent 3. Finds existing memory entries that one piece of human feedback contradicts, narrows or co
PR Feedback Writer
Stage 3 of the PR review pipeline. Turns verified findings from pr-code-analyzer into final, ready-to-post Git
Wsl Worker
Handle git and file operations for the WSL repository /home/ljq/code/PINN/SolvingTeukolsky through the fixed b
Memory Searcher
Searches the long-term memory vault and returns a dense answer with path:line citations. Use for broad questio
Oratores Adversary
Argues against the piece before the room does. Reconstructs every objection at full strength rather than as a
Oratores Strategist
Establishes who a piece is for and what has to change in them, before anything is written. Segments the audien
Related Skills
Stop Rules
Holds your coding agent to your team's written coding rules. A stop hook for Claude Code, Codex, Cursor and te
AI Debate Club
A multi-agent debate engine. Two different LLMs argue any motion, research the web for themselves, and cite th
Onboarding Pack
Onboarding pack skill: the day-one doc — what & why, exact run commands, a map naming the authoritative source