A health check for a prove installation and the project using it. It validates configuration files, required project files, installed tools, and differences between expected and current settings.

Use it to check a project from its root directory and find issues with .claude/.prove.json, CLAUDE.md, the .prove directory, or related tooling.

It helps identify whether a problem comes from missing files, invalid configuration, unavailable tools, or project drift, and reports the severity of each finding.

doctor — Command for Claude Code by mjmorales

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/mjmorales/claude-prove

Made for: Claude Code.

Or install prove, the plugin that ships this one along with the rest of its 25 skills, 30 commands, 21 agents, 5 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/commands/mjmorales/claude-prove/doctor/github.svg)](https://agentmods.dev/commands/mjmorales/claude-prove/doctor)

Your own site

<a href="https://agentmods.dev/commands/mjmorales/claude-prove/doctor"><img src="https://agentmods.dev/badge/commands/mjmorales/claude-prove/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/commands/mjmorales/claude-prove/doctor"><img src="https://agentmods.dev/badge/commands/mjmorales/claude-prove/doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,365 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	$0.00015	$0.01365
Opus 5	$0.00008	$0.00682
Sonnet 5	$0.00003	$0.00273
Haiku 4.5	$0.00002	$0.00136

Measured 9d ago against content hash 5c365a15a6f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

doctor 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.

commands/doctor.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prove Doctor

Validate configs, check tool installation, detect drift. Report by severity tier, then offer fixes.

Output Format

[✓] Check description
[!] Check description — warning detail
[✗] Check description — failure detail
[–] Check description — skipped (reason)

Step 0: Guard

Verify $PLUGIN_DIR is set. If not, error: "Cannot resolve plugin directory."
Verify $(pwd) is NOT inside ~/.claude/. If it is, error: "You are inside the plugin directory. Run this command from your project root."

Stop on any failure.

Step 1: Core Checks

Core checks gate all subsequent tiers. On any failure, skip Steps 2-3 and go to Step 5.

1.1: .claude/.prove.json

claude-prove schema validate --file "$(pwd)/.claude/.prove.json" 2>&1

Pass: valid JSON, no schema errors
Warn: schema warnings (unknown fields)
Fail: missing, invalid JSON, or schema errors — fix: /prove:init

1.2: CLAUDE.md exists

Fail fix: claude-prove claude-md generate --project-root "$(pwd)"

1.3: .prove/ directory exists

Fail fix: mkdir -p .prove

On core failure, print results and skip to Step 5:

── Core ──
[✗] .claude/.prove.json — file not found
[✗] CLAUDE.md — missing
[–] .prove/ directory — skipped (core dependency failed)

Core checks failed. Fix these before other checks can run.

Step 2: Tooling Checks

Only check tools relevant to this project's .claude/.prove.json.

2.0: claude-prove binary on PATH

command -v claude-prove >/dev/null 2>&1

Pass: claude-prove is on $PATH (compiled install)
Warn: not on PATH but $PLUGIN_DIR/packages/cli/bin/run.ts exists — bun-run fallback works, but downstream checks that shell out to bare claude-prove will miss. Fix: bash "$PLUGIN_DIR/scripts/install.sh" (fetches the latest release binary, or refreshes the plugin clone if the binary 404s and falls back to bun run)
Fail: neither available — fix: bash "$PLUGIN_DIR/scripts/install.sh"

Alternative fix (when claude-prove is already on PATH but stale): claude-prove install upgrade atomically swaps in the latest release binary.

Read the full file on GitHub · 184 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.

9d ago First seen · 184 lines · 15 tokens per session scan A 5c365a15a6f4

Subscribe to this mod's changes

doctor is a command published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,365 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

qa-changes

This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…

OpenHands/extensions · 63 tokens

doctor

Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…

doncheli/don-cheli-sdd · 76 tokens

doctor

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Prove Doctor

Output Format

Step 0: Guard

Step 1: Core Checks

1.1: .claude/.prove.json

1.2: CLAUDE.md exists

1.3: .prove/ directory exists

Step 2: Tooling Checks

2.0: claude-prove binary on PATH

What this file has done since we first saw it

Other commands, from other repositories

qa-changes

doctor

fix

doctor

http-service

gh-issue-use-cypress