Skip to main content
subagent CX Codex

experience-curator — Claude Code subagent: what it does

experience-curator — a Claude subagent that screens finished task runs and keeps only verified lessons in ReasoningBank memory.

no license ★ 850 updated 2026-10-26

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/experience-curator.md
Open on GitHub

What experience-curator does

The subagent reads a task history and decides which runs earn a place in ReasoningBank memory. Each run is scored on clarity, reliability, actionability, generalizability and novelty, then weighted into one number. At 0.7 or above the entry is accepted, from 0.5 it goes to review, and anything lower is dropped.

Two hooks in the frontmatter do the fetching. Before the task the agent pulls earlier runs with npx agentic-flow@latest reasoningbank retrieve "$TASK" --with-outcomes; afterwards it distills the result using --quality-filter high. Screening throws out abandoned tasks, runs with no clear verdict and duplicates of patterns already stored. Accepted findings follow a fixed shape: insight, context, evidence, limits and the steps to apply them.

The 0.7 cut is strict. Memory stays clean, yet mid-grade lessons never make it in, and getting them through means editing the weights in the agent file. Both hooks call agentic-flow through npx, so a broken npm setup leaves the subagent as plain text.

What it helps with

  • filter out lessons that duplicate stored memory
  • salvage a usable takeaway from a failed run
  • judge whether a finding generalizes
  • choose what from a task history belongs in memory
  • tell a one-off win from a repeatable trick

Example prompts for the agent

  • Run experience-curator over the last task history and keep only entries above the cut.
  • Pull a lesson worth storing out of the failed run and add it to ReasoningBank.
  • Check the new entries for duplicates against what memory already holds.

How to install experience-curator

Manually: put the files in place

.claude/agents/experience-curator.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about experience-curator

How do I install experience-curator in Claude Code?

Copy the subagent file into .claude/agents/experience-curator.md inside your project. Claude loads subagents from that folder, so nothing else is required.

What does experience-curator do?

It reviews finished task runs and decides which lessons earn a spot in ReasoningBank memory, dropping weak, duplicate or abandoned ones.

What do the 0.7 and 0.5 scores mean?

0.7 or higher accepts the entry, 0.5 to 0.7 sends it to review, and anything below is rejected. Reliability carries the largest weight in the total.

Similar subagents

All subagents for Agent setup: memory, context, orchestration →

From the same set76

The whole set →
Verification & Quality Assurance Verification & Quality Assurance is a Claude Code skill that checks code and agent outputs with reliability scores (0–1.0), reverting failed changes. CX Codex +1 ★ 850repo stars memory-optimizer memory-optimizer is a Claude Code, Codex, and Cursor subagent that merges similar ReasoningBank memories and removes stale or conflicting patterns. It also checks memory quality. CX Codex ★ 850repo stars sync-coordinator sync-coordinator coordinates version alignment, cross-package dependencies, and documentation updates across multiple repositories using an agent swarm. CX Codex ★ 850repo stars reasoning-optimized The reasoning-optimized subagent selects a reasoning strategy based on the task and coordinates five specialist agents. Use it when a task calls for context synthesis, pattern reuse, or curation of results. CX Codex ★ 850repo stars issue-tracker issue-tracker coordinates GitHub issues and task progress using ReasoningBank pattern storage. Fits projects needing structured triage. CX Codex ★ 850repo stars parallel-execution-guide The parallel-execution-guide prompt guides Claude Code through splitting work into independent tasks, spawning CLI subagents, and combining their results. Use it for parallel research or code review. GP ChatGPT ★ 850repo stars architecture A subagent for the Architecture stage of SPARC. It turns pseudocode into a component design, pulls similar patterns from claude-flow memory, and stores what worked. CX Codex ★ 850repo stars Resource Allocator Resource Allocator manages agent swarm capacity through adaptive resource distribution and predictive scaling across CPU, memory, storage, and network channels. CX Codex ★ 850repo stars

Project sponsors

Companies that keep this analytics open