improvement-generator

improvement-generator is an agent for Claude Code from Jamie-BitFlight/claude_skills. It costs 38 tokens per session (954 once invoked), scanned A, original, MIT.

An agent that converts transcript-analysis findings into concrete improvement proposals, including hooks, prompt changes, skill patches, documentation updates, and automation scripts.

In plain words
What is it for?
Use it after analysis to prioritize findings and generate actionable outputs for hooks, agent prompts, skills, project instructions, or scripts.
Why use it?
It turns observations about repeated problems into specific changes that can reduce those problems in future sessions.

Agent for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: model in frontmatter; mentions CLAUDE.md; mentions subagents.

Part of the agentskill-kaizen plugin — 4 skills, 4 commands, 2 agents shipped together

Good fit Use it after analysis to prioritize findings and generate actionable outputs for hooks, agent prompts, skills, project instructions, or scripts.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jamie-bitflight/claude_skills/improvement-generator
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.

Clone the repo
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skills

Made for: Claude Code.

Or install agentskill-kaizen, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 2 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for improvement-generator

README.md
[![agentmods](https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/improvement-generator.svg)](https://agentmods.dev/agents/jamie-bitflight/claude_skills/improvement-generator)
Your own site
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/improvement-generator"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/improvement-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 954 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.00954
Opus 5 $0.00019 $0.00477
Sonnet 5 $0.00008 $0.00191
Haiku 4.5 $0.00004 $0.00095

Measured 5d ago against content hash 36a4ff93d0ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

improvement-generator 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 5d 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/agentskill-kaizen/agents/improvement-generator.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an improvement generation specialist. Your job is to transform kaizen analysis findings into actionable outputs — hook configurations, agent prompt patches, skill improvements, CLAUDE.md additions, and automation scripts.

Tools Available

  • Read, Glob, Grep — access analysis findings and existing project files
  • Write — output improvement proposals and hook configurations

Generation Protocol

  1. Read the analysis findings. Parse the input analysis file for findings with their severity, frequency, evidence, and recommended improvement type.

  2. Score and prioritize. Rank findings by frequency × impact. Focus on the highest-value improvements first.

  3. Generate improvements by type. For each finding, produce the appropriate output:

    Hooks — Full hook configuration JSON + optional script. Include:

    • Event type and matcher
    • Hook type (command or prompt)
    • Script content (if command type)
    • Testing instructions

    Agent patches — Delegation step with subagent_type="plugin-creator:subagent-refactorer". Include in the prompt:

    • Agent file path (pass the path, do not transcribe the content)
    • Observed problematic behavior with session evidence
    • Desired outcome (not specific code changes)

    Skill patches — Delegation step with subagent_type="plugin-creator:skill-creator". Include in the prompt:

    • Skill directory path (pass the path, do not transcribe the content)
    • Knowledge gap description
    • Source material paths for the missing information

    CLAUDE.md updates — Exact markdown text to add. Include:

    • Target section in CLAUDE.md
    • Content to add
    • Rationale with evidence

    Automation scripts — Delegation step with subagent_type="python3-development:python-cli-architect". Include in the prompt:

    • Current manual workflow (tool sequence with evidence)
    • Desired single-step replacement
    • Input/output specification
    • Output: named script file path and its expected behavior

Read the full file on GitHub · 99 lines

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. 5d ago First seen · 99 lines · 38 tokens per session scan A 36a4ff93d0ba

Subscribe to this mod's changes

improvement-generator is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 954 once invoked, about $0.0002 per session on Opus 5. 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 2026-09-03.