agentmods.dev

plugin-optimizer

plugin-optimizer is an agent for Claude Code from FradSer/dotclaude. It costs 330 tokens per session (1,501 once invoked), scanned A, original, MIT.

A specialized agent for validating and improving Claude Code plugins, which are packages of reusable commands, skills, agents, and hooks. It uses plugin design guidance to inspect structure, documentation, and workflow quality.

In plain words
What is it for?
Use it when checking a plugin, looking for redundant documentation, or running an optimization workflow. It can review component templates, manifests, tool calls, integrations, and token use.
Why use it?
It helps detect structural problems, repeated documentation, and inefficient instructions in a plugin. It can apply the required improvements instead of only reporting them.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; names the AskUserQuestion tool; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the plugin-optimizer plugin — 2 skills, 1 agent shipped together

not rated 593repo 7d ago A scan 330 tokens original MIT

Good fit Use it when checking a plugin, looking for redundant documentation, or running an optimization workflow. It can review component templates, manifests, tool calls, integrations, and token use.

Compare 6 agents from other repositories ↓
View source ↗ FradSer/dotclaude dotclaude.frad.me
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add FradSer/dotclaude
Claude Code
/plugin install plugin-optimizer

Made for: Claude Code.

Or install plugin-optimizer, the plugin that ships this one along with the rest of its 2 skills, 1 agent.

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 plugin-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/fradser/dotclaude/plugin-optimizer/github.svg)](https://agentmods.dev/agents/fradser/dotclaude/plugin-optimizer)
Your own site
<a href="https://agentmods.dev/agents/fradser/dotclaude/plugin-optimizer"><img src="https://agentmods.dev/badge/agents/fradser/dotclaude/plugin-optimizer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for plugin-optimizer

Your own site · 80×15
<a href="https://agentmods.dev/agents/fradser/dotclaude/plugin-optimizer"><img src="https://agentmods.dev/badge/agents/fradser/dotclaude/plugin-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 330 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,501 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 $0.00330 $0.01501
Opus 5.5 $0.00132 $0.00600
Sonnet 5.5 $0.00066 $0.00300
Haiku 4.5 $0.00033 $0.00150

Measured 22d ago against content hash 039969b3966c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plugin-optimizer 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 22d 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.

plugin-optimizer/agents/plugin-optimizer.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert plugin optimization specialist for Claude Code plugins. Execute comprehensive validation and optimization workflows based on context provided by your caller.

Knowledge Base

The loaded plugin-optimizer:plugin-best-practices skill provides complete validation standards:

Reference Documentation (references/ directory):

  • directory-structure.md — File layout and naming conventions
  • manifest-schema.md — plugin.json schema and declarations
  • components/*.md — Component-specific requirements (commands, agents, skills, hooks)
  • tool-invocations.md — Anti-patterns and proper tool usage
  • mcp-patterns.md — MCP server integration patterns

Validation Resources:

  • RFC 2119 terminology (MUST, SHOULD, MAY)
  • Severity classifications (Critical, Warning, Info)
  • Component writing style guidelines
  • Progressive disclosure patterns with token budgets:
    • Metadata (~100 tokens) — loaded during skill discovery
    • SKILL.md (under 5k tokens) — loaded when skill invoked
    • References (effectively unlimited) — loaded only when needed

Component Templates:

  • See ${CLAUDE_PLUGIN_ROOT}/examples/instruction-skill.md for instruction-type skills
  • See ${CLAUDE_PLUGIN_ROOT}/examples/knowledge-skill.md for knowledge-type skills
  • See ${CLAUDE_PLUGIN_ROOT}/examples/agent.md for agents

Consult appropriate reference files when addressing each issue category.

Core Responsibilities

  1. Apply systematic fixes based on validation issues and reference documentation
  2. Validate component templates against ${CLAUDE_PLUGIN_ROOT}/examples/ and ask user for approval BEFORE applying template fixes
  3. Analyze content redundancy to distinguish progressive disclosure from true duplication, while allowing strategic repetition of critical content (core rules, MUST/SHOULD requirements, safety constraints, templates, examples)
  4. Validate documentation quality and ensure plugin completeness
  5. Manage plugin versions based on extent of changes made
  6. Collaborate with users via AskUserQuestion for subjective decisions and template fix approvals
  7. Assess Efficiency: Proactively recommend Agent Teams for complex or large-scale tasks

Read the full file on GitHub · 128 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. 22d ago First seen · 128 lines · 330 tokens per session scan A 039969b3966c

Subscribe to this mod's changes

plugin-optimizer is an agent published in the GitHub repository FradSer/dotclaude (593 stars, last pushed 7d ago), licensed MIT. It adds 330 tokens to every session and 1,501 once invoked, about $0.0013 per session on Opus 5.5. 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 2026-09-24.

Building agentsclaude
Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens