improve-plugin

improve-plugin is a command for Claude Code from abossenbroek/abossenbroek-claude-plugins. It costs 0 tokens per session (687 once invoked), scanned A, original, BSD-3-Clause.

A command for improving an existing Claude Code plugin, a package that adds commands or behaviour to Claude Code. It can focus on context handling, agent coordination, or the way agents pass work to one another.

In plain words
What is it for?
Use it with an optional focus such as context, orchestration, or handoff, and an optional plugin path. It finds the plugin configuration, checks that the plugin exists, and launches the improvement coordinator.
Why use it?
It provides a defined entry point for locating a plugin and starting an improvement review. This helps organise changes to the plugin’s instructions and multi-agent workflow.

Command for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: mentions subagents; mentions Claude Code.

Part of the context-engineering plugin — 1 skill, 4 commands shipped together

Good fit Use it with an optional focus such as context, orchestration, or handoff, and an optional plugin path. It finds the plugin configuration, checks that the plugin exists, and launches the improvement coordinator.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/abossenbroek/abossenbroek-claude-plugins/improve-plugin
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/abossenbroek/abossenbroek-claude-plugins

Made for: Claude Code.

Or install context-engineering, the plugin that ships this one along with the rest of its 1 skill, 4 commands.

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 improve-plugin

README.md
[![agentmods](https://agentmods.dev/badge/commands/abossenbroek/abossenbroek-claude-plugins/improve-plugin.svg)](https://agentmods.dev/commands/abossenbroek/abossenbroek-claude-plugins/improve-plugin)
Your own site
<a href="https://agentmods.dev/commands/abossenbroek/abossenbroek-claude-plugins/improve-plugin"><img src="https://agentmods.dev/badge/commands/abossenbroek/abossenbroek-claude-plugins/improve-plugin.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 687 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 $0.00000 $0.00687
Opus 5 $0.00000 $0.00344
Sonnet 5 $0.00000 $0.00137
Haiku 4.5 $0.00000 $0.00069

Measured 7d ago against content hash 4c9365d649e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

improve-plugin 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 7d 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.

context-engineering/commands/improve-plugin.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/improve-plugin Command

Improve an existing Claude Code plugin with SOTA context engineering patterns.

Usage

/improve-plugin [focus] [path]

Arguments

focus (optional):

  • all - Full improvement pass (context + orchestration + handoff) (default)
  • context - Optimize context management (Four Laws)
  • orchestration - Improve agent hierarchy and coordination
  • handoff - Optimize agent-to-agent data transfer

path (optional):

  • Path to plugin directory (default: auto-detect in current workspace)

Instructions

You are the MINIMAL entry point for plugin improvement. Your ONLY job is to:

  1. Parse focus and path arguments
  2. Locate the plugin to improve
  3. Launch the improve-coordinator agent
  4. Return the coordinator's output directly

Step 1: Parse Arguments

Determine focus area and plugin path:

  • Default focus: all
  • Default path: Look for .claude-plugin/plugin.json in workspace

Step 2: Locate Plugin

If no path provided:

  1. Search for .claude-plugin/plugin.json files
  2. If multiple found, ask user to specify
  3. If none found, ask user to provide path

Verify the plugin exists by checking for plugin.json.

Step 3: Launch Coordinator

Use the Task tool to launch the improve-coordinator agent:

Task: Improve plugin with SOTA patterns
Agent: agents/improve-coordinator.md
Prompt:
  plugin_path: [resolved plugin directory]
  focus_area: [parsed focus: all|context|orchestration|handoff]

The coordinator will:

  1. Analyze the plugin structure
  2. Generate improvements based on focus area
  3. Ground improvements (pattern check, token estimate, risk)
  4. Present options for user selection
  5. Generate final improvement report

Step 4: Return Output

Return the coordinator's improvement report DIRECTLY to the user.

DO NOT:

  • Add commentary about the process
  • Explain what the coordinator did
  • Include intermediate analysis
  • Modify the report in any way

ONLY return the final improvement report.

Context Isolation Rules

Read the full file on GitHub · 121 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. 7d ago First seen · 121 lines · 0 tokens per session scan A 4c9365d649e3

Subscribe to this mod's changes

improve-plugin is a command published in the GitHub repository abossenbroek/abossenbroek-claude-plugins (2 stars, last pushed 4mo ago), licensed BSD-3-Clause. It costs nothing until one of its globs matches a file; then it loads 687 tokens. 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.