A development check that inspects a Windows computer’s operating system, runtime, tools, package managers, and isolation settings.

Checking whether required tools or Windows features are present, investigating environment problems, and confirming the machine state after installations or configuration changes.

It shows which facts are confirmed, missing, or unknown before those facts affect the next development step. This helps avoid treating an incomplete check as proof that something is unavailable.

env-inspect — Skill for Claude Code by The-Biomechanist

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 env-inspect

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/the-biomechanist/windows-dev-agent/env-inspect/github.svg)](https://agentmods.dev/skills/the-biomechanist/windows-dev-agent/env-inspect)

Your own site

<a href="https://agentmods.dev/skills/the-biomechanist/windows-dev-agent/env-inspect"><img src="https://agentmods.dev/badge/skills/the-biomechanist/windows-dev-agent/env-inspect/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/the-biomechanist/windows-dev-agent/env-inspect"><img src="https://agentmods.dev/badge/skills/the-biomechanist/windows-dev-agent/env-inspect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 404 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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.00404
Opus 5	$0.00015	$0.00202
Sonnet 5	$0.00006	$0.00081
Haiku 4.5	$0.00003	$0.00040

Measured 9d ago against content hash 7b12a637ecb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

env-inspect 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/env-inspect/SKILL.md · 20 lines

What it actually says

Environment Inspect

Call env_inspect when machine/runtime state can change the next action.
Read the returned snapshot as evidence. Availability values are tri-state:
- true — observed present/enabled;
- false — observed absent/disabled;
- null — the probe did not establish the fact.
Treat top-level status: degraded, snapshot.success: false, or a relevant entry in snapshot.errors as partial evidence. Do not convert an unknown/failed probe into “missing.”
The broad snapshot establishes Windows feature state and executable presence without launching developer binaries for version output. Use tool_discover only when a focused executable/version check can change the route. tool_discover executes discovered programs with a version argument, so it remains on the active host permission surface even though the requested effect is diagnostic. If the executable is present but its version probe fails, preserve version_status: unknown rather than inventing a version.
Treat cached environment state as time-bound. After an install, optional-feature change, PATH/toolchain mutation, or other action that can invalidate the field you are about to consume, prefer the narrow fresh probe; if a full snapshot is required, call env_inspect with force_refresh: true.
Use ecosystem_scan for MCP configs, extensions, project agent config, or host plugin inventory. Project-only inventory is the narrow default; request include_host: true only when user-level state is actually needed.
Suggest a repair only when observed state blocks or materially degrades the requested task.

For package installation, route to the package-install skill and package_search / package_install MCP tools rather than emitting an unreviewed install command.

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.

9d ago First seen · 20 lines · 29 tokens per session scan A 7b12a637ecb8

Subscribe to this mod's changes

env-inspect is a skill published in the GitHub repository The-Biomechanist/Windows-Dev-Agent (0 stars, last pushed 9d ago), licensed MIT. It adds 29 tokens to every session and 404 once invoked, about $0.0001 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.

Debugging DevOps and cloud agent agent-skills agentic-ai agents ai ai-agent

rubber-duck

Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…

kirodotdev/KiroCrew · 161 tokens

ai-discover

Parallel discovery of performance hotspots (perf track) and failure surfaces (bug track) for the auto-improvement loop. Fans out one subagent per hot-path area or failure surface; each returns ONE concrete, behavior-preserving fix candidate (perf) or a reproducing test plus fix (bug). Discovery only — no code changes…

kirodotdev/KiroCrew · 75 tokens

env-inspect

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Environment Inspect

What this file has done since we first saw it

Other skills, from other repositories

rubber-duck

ai-discover

debugging-websocket-issues

systematic-debugging

simplify-code

node-inspect-debugger