agentmods.dev

aws-doctor

aws-doctor is a command for Claude Code from odere-pro/claude-aws-architect. It costs 62 tokens per session (785 once invoked), scanned C, original, MIT.

An AWS environment health check for a cloud-architecture toolkit. AWS is Amazon’s cloud platform; the check verifies the command-line tools, settings, service connections, and required permissions.

In plain words
What is it for?
Use it to check AWS command-line access, profiles and regions, tool packages, enabled service connections, account identity, and minimum permissions.
Why use it?
It shows whether the tools and account are ready before cloud design or deployment work begins, and identifies configuration or access problems.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-aws-architect plugin — 15 skills, 4 commands, 5 agents, 6 MCP servers shipped together

not rated 1repo 1mo ago C scan 62 tokens original MIT

Good fit Use it to check AWS command-line access, profiles and regions, tool packages, enabled service connections, account identity, and minimum permissions.

Compare 6 commands from other repositories ↓
View source ↗ odere-pro/claude-aws-architect
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add odere-pro/claude-aws-architect
Claude Code
/plugin install claude-aws-architect

Made for: Claude Code.

Or install claude-aws-architect, the plugin that ships this one along with the rest of its 15 skills, 4 commands, 5 agents, 6 MCP servers.

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 aws-doctor

README.md
[![agentmods](https://agentmods.dev/badge/commands/odere-pro/claude-aws-architect/aws-doctor/github.svg)](https://agentmods.dev/commands/odere-pro/claude-aws-architect/aws-doctor)
Your own site
<a href="https://agentmods.dev/commands/odere-pro/claude-aws-architect/aws-doctor"><img src="https://agentmods.dev/badge/commands/odere-pro/claude-aws-architect/aws-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 aws-doctor

Your own site · 80×15
<a href="https://agentmods.dev/commands/odere-pro/claude-aws-architect/aws-doctor"><img src="https://agentmods.dev/badge/commands/odere-pro/claude-aws-architect/aws-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 785 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 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 $0.00062 $0.00785
Opus 5 $0.00031 $0.00392
Sonnet 5 $0.00012 $0.00157
Haiku 4.5 $0.00006 $0.00078

Measured 10d ago against content hash fc4f3ba68c46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

aws-doctor scanned grade C 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 10d 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- This command does not modify `.mcp.json`, `${HOME}/.aws/credentials`, or any consumer file.
commands/aws-doctor.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running the claude-aws-architect doctor — an in-session environment health check.

Inputs

  • Arguments: $ARGUMENTS (optional --json flag for structured output).
  • Plugin root: ${CLAUDE_PLUGIN_ROOT} — resolves to scripts/doctor.sh when the scripts bundle is installed.

Action

  1. Resolve the doctor script path: ${CLAUDE_PLUGIN_ROOT}/scripts/doctor.sh.
  2. If the script exists, execute it via Bash with the user-supplied arguments forwarded verbatim. The script verifies:
    • uvx (and underlying uv) is installed and on PATH.
    • aws CLI is installed and on PATH.
    • AWS_PROFILE and AWS_REGION are set in the environment.
    • Every stdio MCP server declared in ${CLAUDE_PLUGIN_ROOT}/.mcp.json resolves via uvx.
    • Every declared MCP server is enabled (or approval-pending) per the consumer's .claude/settings*.json — flags any server explicitly listed in disabledMcpjsonServers.
    • aws sts get-caller-identity succeeds against the resolved profile.
    • The minimum IAM permission set required by the plugin's MCP servers is present.
  3. If the script does not exist yet (the scripts bundle has not been installed), emit a clearly-marked notice: the script ships in a later integration step; report which environment checks the user can run manually in the meantime.

Exit-code mapping

When the script ran:

  • 0 — environment is healthy.
  • 1 — a required tool (uvx, aws) is missing.
  • 2 — required environment variables (AWS_PROFILE, AWS_REGION) are missing.
  • 3 — at least one MCP server failed to resolve.
  • 4 — sts:GetCallerIdentity failed (credentials, MFA, or expired session).
  • 5 — minimum-IAM presence check failed.
  • 6 — one or more MCP servers declared in .mcp.json are explicitly disabled in the consumer's .claude/settings*.json. The user must re-enable via /mcp or by removing the server from disabledMcpjsonServers before recipes that depend on it can ground.

Surface the exit code in the user-facing response. On non-zero exit, point the user at the next step (rotate credentials, set the env var, install the missing tool, enable the disabled MCP via /mcp) instead of emitting a wall of stack output.

Read the full file on GitHub · 56 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. 10d ago First seen · 56 lines · 62 tokens per session scan C fc4f3ba68c46

Subscribe to this mod's changes

aws-doctor is a command published in the GitHub repository odere-pro/claude-aws-architect (1 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 785 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeCloudDevOps and cloudagentic-aiai-agentsawsaws-cdkclaude-code-plugin
Related

Other commands, from other repositories

progress

View your CodeSensei learning dashboard — belt rank, XP, streaks, and skills.

wewpellex21/code-sensei · 18 tokens

recap

Get a summary of everything you learned this session — concepts, quizzes, and progress.

wewpellex21/code-sensei · 16 tokens

caiq-generate

Generate CAIQ (Consensus Assessments Initiative Questionnaire) responses.

GRCEngClub/claude-grc-engineering · 11 tokens

map-framework

Map CSA CCM controls to other compliance frameworks.

GRCEngClub/claude-grc-engineering · 8 tokens

cccs-guidance

CCCS assessment process and certified cloud provider guidance.

GRCEngClub/claude-grc-engineering · 9 tokens

AWS Inspector Collect

Query AWS for compliance-relevant configuration across IAM, S3, CloudTrail, EBS, and emit findings conforming to the v1 contract.

GRCEngClub/claude-grc-engineering · 34 tokens