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.
npx skills add The-Biomechanist/Windows-Dev-Agent --skill ecosystem-defraggit clone --depth 1 https://github.com/The-Biomechanist/Windows-Dev-AgentWrote 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.
[](https://agentmods.dev/skills/the-biomechanist/windows-dev-agent/ecosystem-defrag)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
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.
- 9d ago First seen · 57 lines · 33 tokens per session scan A ea3c82d9ee16
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.
Other skills, from other repositories
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…
meetings
Context for working with the Meetings app's data — where a meeting's notes, diagram, transcript-derived tasks, and calendar cache live, what the lifecycle states mean, and how the app's agents are driven. Load when the user asks about a meeting's notes or action items, or when writing/reading files under the meetings…
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
pto-planning
Check an employee's PTO balance and policy, then plan or submit a time-off request.
mochi-tips
Feature tips catalog for new users. Plan skill loads this to pick a tip during the first week.
bootstrap
Onboarding conversation to generate a user profile.