What is environment-doctor?

A diagnostic checker for a Claude Code development setup. It checks tools such as Git, Node.js, Bun, VS Code, Docker, Claude Code, claude-mem, and related extensions or plugins.

Use it when setting up a machine, investigating a broken development environment, or checking whether required tools and extensions are installed.

It shows which parts of a development environment are missing, outdated, or not running. It also provides operating-system-specific commands for suggested fixes.

environment-doctor — Skill for Claude Code by killernay

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 killernay/cc-devenv-doctor --skill environment-doctor

Clone the repo

git clone --depth 1 https://github.com/killernay/cc-devenv-doctor

Made for: Claude Code.

Or install devenv-doctor, the plugin that ships this one along with the rest of its 1 skill.

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/killernay/cc-devenv-doctor/environment-doctor/github.svg)](https://agentmods.dev/skills/killernay/cc-devenv-doctor/environment-doctor)

Your own site

<a href="https://agentmods.dev/skills/killernay/cc-devenv-doctor/environment-doctor"><img src="https://agentmods.dev/badge/skills/killernay/cc-devenv-doctor/environment-doctor/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/killernay/cc-devenv-doctor/environment-doctor"><img src="https://agentmods.dev/badge/skills/killernay/cc-devenv-doctor/environment-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,715 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 3 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	$0.00092	$0.01715
Opus 5.5	$0.00037	$0.00686
Sonnet 5.5	$0.00018	$0.00343
Haiku 4.5	$0.00009	$0.00171

Measured 8d ago against content hash 5d8f3993ce7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

environment-doctor scanned grade D with 3 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 8d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- Missing Claude Code CLI → `curl -fsSL https://claude.ai/install.sh | bash`

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **Codex: wrong subcommand.** Codex installs with `codex plugin add`, not `install`. There is no scope flag; the enabled state lives in `~/.codex/config.toml` under `[plugins."<name>@<marketplace>"]` — `enabled = false`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Missing Claude Code CLI → `curl -fsSL https://claude.ai/install.sh | bash`

devenv-doctor/skills/environment-doctor/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This skill runs inside either Claude Code or Codex. Every check below is read-only. In Claude Code they are pre-approved in allowed-tools, so run them without stopping to ask. Never assume a result — always run the real command.

If a check fails with "Operation not permitted", "permission denied", or a Docker socket connect error while you are running inside Codex, that is Codex's sandbox, not the machine: rerun that one command with escalated permissions before reporting it as broken.

1. Run these checks (one at a time)

git --version
node --version (needs ≥ 20 — claude-mem requires it; current LTS recommended)
code --version
docker --version and docker info (confirms the engine is actually running, not just installed)
Claude Code, if it's installed:
- claude --version
- claude doctor — read-only install diagnostics; reports sign-in state, auto-update state, settings-file errors, each with a suggested fix
- claude plugin list and claude plugin marketplace list
Codex, if it's installed:
- codex --version
- codex doctor --summary --no-color — read-only; reports auth (no Codex credentials = not logged in), sandbox, connectivity, available updates
- codex plugin list and codex plugin marketplace list
claude-mem: test -d ~/.claude-mem (installed at all), claude-mem --version (the hook launcher is on PATH), bun --version (its hooks and worker run on Bun)
code --list-extensions and check for: anthropic.claude-code (if Claude Code is used), openai.chatgpt (if Codex is used), ms-azuretools.vscode-containers (Docker support; the older ms-azuretools.vscode-docker is now just a pack that pulls it in — either counts)

At least one agent CLI must be present. Only report the other one as missing if the user says they use it.

Summarize the results as a ✅/❌ table before suggesting any fixes.

2. Fix commands by OS (ask which OS if unknown)

Windows (PowerShell):

Missing Git → winget install --id Git.Git -e
Missing Node → winget install --id OpenJS.NodeJS.LTS -e
Missing VS Code → winget install --id Microsoft.VisualStudioCode -e
Missing Docker → winget install --id Docker.DockerDesktop -e, then note it needs a restart + first manual launch (and wsl --install --no-distribution first if WSL2 isn't set up yet)
Missing Claude Code CLI → irm https://claude.ai/install.ps1 | iex
Missing Codex CLI → irm https://chatgpt.com/codex/install.ps1 | iex

Read the full file on GitHub · 95 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.

8d ago Changed · +23 lines · +51 tokens per session scan C → D 5d8f3993ce7f
2mo ago First seen · 72 lines · 41 tokens per session scan C 8aff63fd1677

Subscribe to this mod's changes

environment-doctor is a skill published in the GitHub repository killernay/cc-devenv-doctor (13 stars, last pushed 4d ago), licensed MIT. It adds 92 tokens to every session and 1,715 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Debugging bash bootstrap claude-code-plugin dev-environment developer-tools

logs

Use when the user wants to check Tandem's activity log, review errors, or debug hook behavior. Also use when the user mentions 'tandem logs', 'what happened', or 'tandem errors'.

jonny981/claude-tandem · 44 tokens

tidewave-integration

Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.

oliver-kriska/claude-elixir-phoenix · 38 tokens

anti-patterns

Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).

avelikiy/great_cto · 59 tokens

windows-compat

Audit and harden this Rust repo (code-graph-mcp) for Windows correctness: path-spelling drift between producers, the 32,767-char command-line cap, index-key mismatches, and path predicates that assume one ecosystem's layout. Use whenever touching code that builds, compares, prints, or stores a filesystem path; that…

sdsrss/code-graph-mcp · 165 tokens

resolving-merge-conflicts

Use when a git merge or rebase reports conflicts and the operation is in progress.

romiluz13/cc10x · 25 tokens

chaos

Design, run, and debug Chaos Engineering experiments on Kubernetes using Litmus Chaos v3 and Chaos Mesh v2. Covers fault injection (pod-delete, network-loss, CPU stress, node-drain), steady-state hypothesis probes, GameDay runbooks, scheduled experiments, DORA feedback loop, and RBAC setup. Use when asked to "inject a…

nitinjain999/platform-skills · 97 tokens

environment-doctor