ecosystem-defrag

ecosystem-defrag is a skill for Claude Code from The-Biomechanist/Windows-Dev-Agent. It costs 33 tokens per session (671 once invoked), scanned A, original, MIT.

A procedure for reviewing a Windows coding-agent setup and finding duplicated capabilities across its tools, plugins, instructions, and configuration.

In plain words
What is it for?
Use it to inventory project or host configuration, compare concrete overlaps, and consolidate fragmented agent tooling when needed.
Why use it?
It helps when several tools overlap or contradict each other. It supports a justified cleanup plan and keeps changes reversible and verifiable.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions Codex.

Part of the windows-dev-agent plugin — 6 skills, 3 commands, 4 hooks, 1 MCP server shipped together

Good fit Use it to inventory project or host configuration, compare concrete overlaps, and consolidate fragmented agent tooling when needed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/the-biomechanist/windows-dev-agent/ecosystem-defrag
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.

Any agent
npx skills add The-Biomechanist/Windows-Dev-Agent --skill ecosystem-defrag
Clone the repo
git clone --depth 1 https://github.com/The-Biomechanist/Windows-Dev-Agent

Made for: Claude Code.

Or install windows-dev-agent, the plugin that ships this one along with the rest of its 6 skills, 3 commands, 4 hooks, 1 MCP server.

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 ecosystem-defrag

README.md
[![agentmods](https://agentmods.dev/badge/skills/the-biomechanist/windows-dev-agent/ecosystem-defrag/github.svg)](https://agentmods.dev/skills/the-biomechanist/windows-dev-agent/ecosystem-defrag)
Your own site
<a href="https://agentmods.dev/skills/the-biomechanist/windows-dev-agent/ecosystem-defrag"><img src="https://agentmods.dev/badge/skills/the-biomechanist/windows-dev-agent/ecosystem-defrag/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 ecosystem-defrag

Your own site · 80×15
<a href="https://agentmods.dev/skills/the-biomechanist/windows-dev-agent/ecosystem-defrag"><img src="https://agentmods.dev/badge/skills/the-biomechanist/windows-dev-agent/ecosystem-defrag.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 671 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 $0.00033 $0.00671
Opus 5 $0.00016 $0.00336
Sonnet 5 $0.00007 $0.00134
Haiku 4.5 $0.00003 $0.00067

Measured 9d ago against content hash ea3c82d9ee16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ecosystem-defrag 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 9d 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.

skills/ecosystem-defrag/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ecosystem Defrag

Use this when the agent/developer-tool environment itself has become duplicated, contradictory, or hard to maintain. A clean inventory with no justified change is a valid terminal result.

1. Establish the inventory

Start with ecosystem_scan for the current project and include_host: false. This bounded scan owns project-local VS Code recommendations, MCP config, and agent configuration such as .clinerules, .roo/, .continue/, .agents/, Copilot instructions, and CLAUDE.md when present.

Request include_host: true only when user-level extensions, plugins, MCP configuration, or installed package state is actually needed to decide the consolidation. That broader read remains on the active host permission surface. Use include_packages: true only together with include_host: true and only when installed WinGet packages matter.

In Codex, ecosystem_scan remains on native approval even for project-only requests. The adapter requires a caller-supplied cwd but cannot independently prove that an arbitrary supplied directory is the active project, so the optional trusted hook does not auto-approve this filesystem inventory read.

Do not invent enabled/disabled plugin state or configuration meaning the scan cannot establish. Treat unavailable host-owned state as unknown unless an authoritative host surface is actually queried.

2. Build the overlap map

For each discovered item, distinguish:

  • specialist — owns a domain Windows Dev Agent should route to rather than absorb;
  • orchestration overlap — duplicates planning, generic shell routing, MCP aggregation, package/install orchestration, or environment discovery;
  • configuration only — instructions or project policy that should be preserved as input;
  • unknown — purpose or ownership is not established yet.

Do not recommend removal merely because two tools are both agentic. Name the concrete duplicated capability or leave the relationship unresolved.

3. Choose the smallest justified mode

Read the full file on GitHub · 57 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. 9d ago First seen · 57 lines · 33 tokens per session scan A ea3c82d9ee16

Subscribe to this mod's changes

ecosystem-defrag is a skill published in the GitHub repository The-Biomechanist/Windows-Dev-Agent (0 stars, last pushed 9d ago), licensed MIT. It adds 33 tokens to every session and 671 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 2026-08-31.