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 package-installgit 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/package-install)<a href="https://agentmods.dev/skills/the-biomechanist/windows-dev-agent/package-install"><img src="https://agentmods.dev/badge/skills/the-biomechanist/windows-dev-agent/package-install.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.00567 |
| Opus 5 | $0.00020 | $0.00283 |
| Sonnet 5 | $0.00008 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
package-install 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.
How it starts
The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Package Install
Package installation is approval-required. The executing MCP call contains the reviewed mutation and execute: true; the active host asks for permission around that same call. Do not invent a second model-supplied flag that claims approval happened before the host has actually asked.
package_search is non-mutating by intent, but it executes the selected package manager and may contact its configured source. It therefore remains on the active host permission surface rather than being silently auto-approved. package_install also remains host-controlled; in Codex, only execute: false plan calls may be auto-approved by the optional trusted PermissionRequest hook.
Procedure
- Establish package identity before mutation. Preserve an exact package ID supplied by the user or authoritative project/config state. Otherwise call
package_search, inspect the candidates, and resolve the exact identity. Do not guess an ID from naming conventions. - Call
package_installwithexecute: false. Present the returned source, exact package ID, argv, command, and agreement flags as the planned mutation. - When installation is actually requested, call the same tool with
execute: true. The active host's permission system decides whether that exact call proceeds. - Inspect stdout/stderr, return code, and
execution_started. Do not infer success from installer invocation. A failed installer can still partially mutate host state. - Verify the resulting host state on the narrowest relevant surface: executable discovery, version output, or the task-specific check that required the package. Any executed install attempt invalidates the cached environment snapshot. If a full snapshot is needed afterward, use fresh state.
Routing
- WinGet is the default for Windows runtimes and developer tools.
- Chocolatey or Scoop are fallbacks only when the requested package is intentionally sourced there.
- Windows optional features such as WSL, Windows Sandbox, or Hyper-V are not package installs; use an explicitly approved host PowerShell action when the feature is actually required.
- Language package managers (
pip,uv,npm,cargo) belong to the project/runtime workflow and should not be smuggled through this system-package tool.
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.
- 7d ago First seen · 33 lines · 40 tokens per session scan A 1d703be812b5
package-install is a skill published in the GitHub repository The-Biomechanist/Windows-Dev-Agent (0 stars, last pushed 7d ago), licensed MIT. It adds 40 tokens to every session and 567 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
cost-efficiency-analyzer
Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…
executive-financial-briefing
Generates a concise executive-level financial briefing or summary suitable for a CEO, CFO, or board presentation. Use when the user asks for a summary, briefing, executive summary, board update, financial overview, financial health check, or "how is the business doing". Covers the full P&L picture in one page. Also…
multi-quarter-trend-analysis
Analyzes financial trends across multiple quarters by comparing P&L metrics over time. Use when the user wants to see trends, patterns, trajectories, or directional movement across 3 or more quarters. Also use for "how are we trending", "show me the trend", "track performance over time", "quarter over quarter…
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
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…
sector-rotation
Identify which market sectors to overweight or underweight based on current macro conditions and sector performance data.