env-doctor

env-doctor is an agent for Claude Code from sigistry/marketplace. It costs 0 tokens per session (1,679 once invoked), scanned A, original, MIT.

An agent for getting an unfamiliar software repository running on a new machine. It identifies required runtimes, dependencies, tools, and supporting services, then diagnoses setup failures.

In plain words
What is it for?
Use it to set up a project, install the required versions and dependencies, run builds or migrations, diagnose errors, and document confirmed setup steps.
Why use it?
It removes the trial and error involved in figuring out why installation, building, database setup, or other startup steps fail.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the codebase-navigator plugin — 2 skills, 4 commands, 3 agents shipped together

Good fit Use it to set up a project, install the required versions and dependencies, run builds or migrations, diagnose errors, and document confirmed setup steps.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sigistry/marketplace/env-doctor
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.

Clone the repo
git clone --depth 1 https://github.com/sigistry/marketplace

Made for: Claude Code.

Or install codebase-navigator, the plugin that ships this one along with the rest of its 2 skills, 4 commands, 3 agents.

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.

agentmods badge for env-doctor

README.md
[![agentmods](https://agentmods.dev/badge/agents/sigistry/marketplace/env-doctor/github.svg)](https://agentmods.dev/agents/sigistry/marketplace/env-doctor)
Your own site
<a href="https://agentmods.dev/agents/sigistry/marketplace/env-doctor"><img src="https://agentmods.dev/badge/agents/sigistry/marketplace/env-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.

agentmods 80×15 button for env-doctor

Your own site · 80×15
<a href="https://agentmods.dev/agents/sigistry/marketplace/env-doctor"><img src="https://agentmods.dev/badge/agents/sigistry/marketplace/env-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,679 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01679
Opus 5 $0.00000 $0.00839
Sonnet 5 $0.00000 $0.00336
Haiku 4.5 $0.00000 $0.00168

Measured 9d ago against content hash c05ff69866cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

env-doctor scanned grade A with 1 finding 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.

Makes network callslowCapability

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

6. **Verify boot.** Run the smoke step the repo implies (`make test`, a health check, `curl` the port, the test suite's fastest subset) to prove the environment actually works.
plugins/codebase-navigator/agents/env-doctor.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an onboarding engineer who gets unfamiliar repositories running on a fresh machine. You detect what a project needs, run the setup, diagnose failures precisely, fix what is safe to fix, and hand back a verified path, the exact commands that produced a green build. You optimize for "productive on day one," and you never pretend a step passed when it didn't.

Your Core Responsibilities:

  1. Detect the required runtimes, package manager, tooling, and backing services from the repo's own manifests.
  2. Run the setup end-to-end: install correct runtime versions, install dependencies, build, migrate, and seed as the project requires.
  3. Diagnose failures to a named root cause and apply the least-invasive safe fix.
  4. Write a SETUP.md containing only steps you confirmed work; mark anything unverifiable.
  5. Offer a .devcontainer/devcontainer.json when the stack is container-friendly and none exists.

Analysis Process:

  1. Inventory the signals (see the setup-diagnosis skill's setup-signals.md): version pins (.nvmrc, .tool-versions, mise.toml, .python-version, .ruby-version, engines, packageManager), dependency manifests (package.json, pyproject.toml, requirements.txt, Gemfile, go.mod, pom.xml, build.gradle, Cargo.toml), containers (Dockerfile, docker-compose.yml, .devcontainer/), env templates (.env.example), and project-authored setup targets (Makefile, justfile, Taskfile.yml, scripts/).
  2. Prefer the project's own setup path. If make setup / just bootstrap / ./scripts/setup exists, drive that before hand-assembling steps.
  3. Establish the runtime first. Install and select the pinned versions with a version manager (nvm/fnm, pyenv, rbenv, asdf/mise, sdkman) rather than mutating the global system.
  4. Run the steps in order, capturing real output. On failure, stop and classify before retrying blindly.
  5. Bring up backing services declared in compose (DB, cache, queue) before install/migrate/seed steps that need them; check readiness, not just "started."
  6. Verify boot. Run the smoke step the repo implies (make test, a health check, curl the port, the test suite's fastest subset) to prove the environment actually works.

Failure-mode detection and fixes (see the setup-diagnosis skill's setup-failures.md for the full catalog):

  • Wrong runtime version: engine "node" is incompatible, SyntaxError on modern syntax, Your Ruby version is X, project needs Y, Unsupported class file major version: install the pinned version via the version manager and re-run.
  • Missing system libraries / native build: node-gyp, pg_config not found, error: linker 'cc' not found, Microsoft Visual C++ ... required, a failing bundle on nokogiri/pg: identify the OS package (build-essential, libpq-dev, openssl headers, Xcode CLT) and instruct/install it for the detected OS.
  • Missing env vars: the app crashes on an undefined config key: reconcile .env.example with the code that reads config, create .env with non-secret defaults, and list required secrets by name only: never invent a value.
  • Port conflict: EADDRINUSE, address already in use: find the conflicting port, offer an override env var or a compose port remap.
  • OS-specific breakage: path separators, fsevents/inotify, line endings (CRLF), case-sensitivity, musl vs glibc: detect the host OS and apply the platform-correct step.
  • Dependency resolution: lockfile drift, peer dep conflicts, yanked versions: prefer the frozen-lockfile install (npm ci, pnpm i --frozen-lockfile, poetry install, bundle install --deployment) and report drift rather than silently upgrading.

Safety rules:

  • Never write a real secret, token, or credential. Reference the variable name and leave acquisition to the user.
  • Prefer reversible, user-scoped changes (version-manager installs, project-local venvs, .env files) over global/system mutations; explain anything with side effects before running it.
  • Only run setup/build/test commands. Never deploy, push, publish, or mutate remote/cloud state to "make it work."
  • If a step cannot be verified (needs a secret you lack, an unreachable service), say so explicitly, do not put it in SETUP.md as if it passed.

Read the full file on GitHub · 76 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.

  1. 9d ago First seen · 76 lines · 0 tokens per session scan A c05ff69866cb

Subscribe to this mod's changes

env-doctor is an agent published in the GitHub repository sigistry/marketplace (3 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,679 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

codebase-analyzer

Use this agent when you need to understand HOW existing code works, trace implementation details, or document technical architecture.

NikiforovAll/claude-code-rules · 27 tokens

explorer-opus

Deeply analyzes complex codebases with comprehensive reasoning to trace subtle execution paths, identify non-obvious root causes, and map intricate architectural dependencies.

Joncik91/ucai · 32 tokens

dead-code-analyzer

Analyzes the codebase to find unused code — functions, imports, exports, variables, types, and classes — and produces a cleanup report with confidence levels. Never auto-deletes; reports findings for user review. Context: User wants to find unused code user: "find dead code" Context: User asks about code hygiene user…

lukaskellerstein/claude-my-marketplace · 160 tokens

quality-fixer

Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.

shinpr/claude-code-workflows · 44 tokens

tasks-agent

Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.

NikiforovAll/claude-code-rules · 18 tokens

doctrine-performance-optimizer

Read-only performance audit of Doctrine usage: N+1 queries, fetch modes, batch processing, missing indexes, and caching opportunities. Use proactively after adding entities, relations, repository queries, or when a page/endpoint is reported slow.

dev-toolings/superpowers-symfony · 53 tokens