flywheel

A local, plain-text system that helps an AI assistant choose the right skill and improve its behaviour from your corrections. A skill is a reusable set of instructions for a particular kind of task.

In plain words
What is it for?
Use it to manage skill invocation and keep improvement notes on your own computer. It is aimed at workflows where an AI assistant repeatedly performs related tasks.
Why use it?
It is intended to reduce repeated mistakes and make skill selection more reliable over time. The information provided does not describe its exact learning process.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add WinterDDo/claude-skill-flywheel
agentmods
npx agentmods add plugins/winterddo/claude-skill-flywheel/flywheel
Clone the repo
git clone --depth 1 https://github.com/WinterDDo/claude-skill-flywheel

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

flywheel scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/flywheel/.claude-plugin/plugin.json · 12 lines

What it actually says

{
  "name": "flywheel",
  "description": "Self-improving skill system: makes Claude reliably invoke the right skill every turn and learn from your corrections over time. 100% local plaintext.",
  "version": "0.1.1",
  "author": {
    "name": "WinterDDo"
  },
  "homepage": "https://github.com/WinterDDo/claude-skill-flywheel",
  "repository": "https://github.com/WinterDDo/claude-skill-flywheel",
  "license": "MIT"
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 12 lines scan A 387033fd04ee

Subscribe to this mod's changes

flywheel is a plugin published in the GitHub repository WinterDDo/claude-skill-flywheel (2 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other plugins, from other repositories

ai-engineer

Use this agent when implementing AI/ML features, integrating language models, building recommendation systems, or adding intelligent automation to applications. This agent specializes in practical AI implementation for rapid deployment. Examples:\n\n \nContext: Adding AI features to an app\nuser: "We need AI-po.

ccplugins/awesome-claude-code-plugins · not measured

adamsreview

Multi-lens code review pipeline: deep review (Claude or Codex), automated fix loop, interactive walkthrough, manual promote, external-finding injection.

ccplugins/awesome-claude-code-plugins · not measured

instructions-audit

A prompt-injection tripwire for instruction files. An InstructionsLoaded hook audits CLAUDE.md / .claude/rules/.md content as it enters context and flags hidden or hostile directives: invisible Unicode smuggling (zero width characters, tag characters, variation-selector runs; the TrapDoor supply-chain signature), bidi.

karanb192/claude-code-hooks · not measured

pr-provenance-stamp

Embeds a reviewer-facing provenance receipt into your PR body when Claude runs gh pr create (or glab mr create). A PostToolUse hook (async, zero added latency) records a per-session ledger: tool calls, agent-authored lines, and every test/typecheck command with its real exit code; a PreToolUse (Bash) hook then rewr.

karanb192/claude-code-hooks · not measured

git-safety

Branch-aware git guardrails for Claude Code. A PreToolUse hook on Bash that denies destructive git and gh CLI operations before they run: pushing to main/master, deleting protected branches, commit/merge/rebase/reset/push while on a protected branch, and gh pr merge/close, issue close, release delete, repo delete.…

karanb192/claude-code-hooks · not measured

api-authentication

Secure API authentication with JWT, OAuth 2.0, API keys. Use for authentication systems, third-party integrations, service-to-service communication, or encountering token management, security headers, auth flow errors.

secondsky/claude-skills · not measured