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 agentmods add commands/mitulgarg/env-doctor/installgit clone --depth 1 https://github.com/mitulgarg/env-doctorWhat 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 | $0.00000 | $0.00494 |
| Opus 5 | $0.00000 | $0.00247 |
| Sonnet 5 | $0.00000 | $0.00099 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
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 3d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
install
Get the safe install command for GPU libraries that matches your driver.
Usage
env-doctor install <library>
Supported Libraries
torch/pytorch- PyTorch with correct CUDA wheelstensorflow- TensorFlow with GPU supportjax- JAX with CUDA support
How It Works
- Detects your NVIDIA driver version
- Determines the maximum CUDA version your driver supports
- Looks up the correct wheel URL for that CUDA version
- Outputs the exact
pip installcommand
Example
env-doctor install torch
Output:
🔍 Detecting your GPU environment...
🎮 GPU Driver: 535.146.02
└─ Max CUDA: 12.2
⬇️ Run this command to install the SAFE version:
---------------------------------------------------
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu121
---------------------------------------------------
💡 This installs PyTorch built for CUDA 12.1, which is compatible
with your driver (supports up to CUDA 12.2).
Why This Matters
The default pip install torch gives you the latest wheel, which might be built for CUDA 12.4. If your driver only supports CUDA 11.8, you'll get cryptic errors like:
RuntimeError: CUDA error: no kernel image is available for execution on the device
Env-Doctor prevents this by prescribing the correct version for your hardware.
Common Scenarios
Older Driver
$ env-doctor install torch
🎮 GPU Driver: 470.82.01
└─ Max CUDA: 11.4
⬇️ Run this command to install the SAFE version:
---------------------------------------------------
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu113
---------------------------------------------------
No GPU Detected
$ env-doctor install torch
⚠️ No NVIDIA GPU detected
⬇️ Installing CPU-only version:
---------------------------------------------------
pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu
---------------------------------------------------
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.
- 3d ago First seen · 90 lines · 0 tokens per session scan A 94f66ae1e290
install is a command published in the GitHub repository mitulgarg/env-doctor (172 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 494 tokens. 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 2026-08-30.
Other commands, from other repositories
add-language
新しい言語を piper-plus に追加するためのガイドです。引数 $ARGUMENTS に言語コード (例: de, it, da) を指定してください。.
pina-agentic
../../.opencode/commands/pina-agentic.md.
review-language
Command "review-language" from ayutaz/piper-plus, covering 新言語実装レビュー, 前提条件, レビュー手順, step 1: 10エージェント並列レビュー and step 2: レビュー結果集約.
initref
Build a reference for the implementation details of this project. Use provided summarize tool to get summary of the files. Avoid reading the content of many files yourself, as we might hit usage limits. Do read the content of important files though. Use the returned summaries to create reference files in /ref…
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.