Skip to main content
subagent CX Codex

adaptive-learner — Claude Code subagent: what it does, how to install

adaptive-learner — a subagent that pulls similar past cases from ReasoningBank before it starts and files the outcome afterwards, so later runs lean on what already happened.

no license ★ 850 updated 2026-10-26

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

What adaptive-learner does

The agent works in a loop instead of starting cold. Before a task it asks ReasoningBank for related memories, then executes, then judges how the run went, then stores a short lesson. The pre and post hooks in the agent file handle both ends without you prompting them.

Ranking is weighted: semantic similarity carries 65%, past reliability 20%, recency 15%, diversity 10%. Only the top three come back, which keeps the context small. Failures get stored too, as approaches to avoid next time. Hook commands tag entries with the adaptive-learning domain.

Both hooks shell out to npx agentic-flow@latest, so a machine without npx or npm registry access gets none of the memory behaviour — a plain prompt and no loop.

What it helps with

  • reuse a past JWT auth fix instead of starting from zero
  • find out why the earlier debugging pass did not hold
  • keep a working error-handling pattern in agent memory
  • compare iterations of an API design by success rate
  • track how token spend falls when a task repeats

Example prompts for the agent

  • Use the adaptive-learner subagent to add JWT auth and check what earlier attempts in the adaptive-learning domain got wrong.
  • Hand this to adaptive-learner: figure out why auth.spec.ts fails, then distill the finding into memory.
  • Ask adaptive-learner to draft the REST endpoints and compare the result against the last two runs.

How to install adaptive-learner

Manually: put the files in place

.claude/agents/adaptive-learner.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 adaptive-learner

How do I install adaptive-learner in Claude Code?

Put the agent file at .claude/agents/adaptive-learner.md.

What does adaptive-learner do?

It looks up related past tasks in ReasoningBank before starting and stores a short review after finishing. Its approach shifts between runs as a result.

What does the memory layer need in order to run?

The hooks call npx agentic-flow@latest, so npx and access to the npm registry are required. Entries are tagged with the adaptive-learning domain.

Similar subagents

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

From the same set76

The whole set →
code-review-swarm code-review-swarm sends a pull request through several review agents at once: security, performance, style, architecture. Handy when a plain diff and a linter no longer catch the trouble. CX Codex +1 ★ 850repo stars swarm-issue swarm-issue is a Claude Code command that connects GitHub Issues to swarm work by splitting tasks into subtasks, suggesting agents, and tracking progress. It supports workflows managed through GitHub Issues. CX Codex +1 ★ 850repo stars project-board-sync project-board-sync keeps a GitHub Projects board in step with a claude-flow agent swarm: cards, statuses, sprint metrics. Useful when several agents touch one repo. CX Codex ★ 850repo stars release-manager release-manager coordinates release pipelines using an agent swarm. It synchronizes versions across packages, executes tests, and opens a GitHub pull request. CX Codex +1 ★ 850repo stars pagerank-analyzer The pagerank-analyzer subagent computes PageRank and examines graph structure. Use it to find influential nodes or assess connections across a network. CX Codex ★ 850repo stars production-validator production-validator — a subagent that hunts leftover mocks and stubs in your code, then runs the tests against a real database, cache and payment API before you deploy. CX Codex ★ 850repo stars multi-repo-swarm multi-repo-swarm coordinates AI swarms across multiple repositories with the GitHub CLI and ruv-swarm. Useful for cross-project updates. CX Codex +1 ★ 850repo stars coder The coder subagent implements and refactors code, designs APIs, and handles errors. Use it for development tasks that call for tests and follow-up checks. CX Codex ★ 850repo stars

Project sponsors

Companies that keep this analytics open