agentmods.dev

doctor

doctor is an agent for coding agents from mauhpr/agentlint-plugin. It costs 11 tokens per session (474 once invoked), scanned A, original, MIT.

A diagnostic agent for AgentLint, a tool that checks coding-agent configuration and installed hooks. It examines settings, rules, custom checks, and command-line integrations.

In plain words
What is it for?
Use it to run diagnostics, validate AgentLint configuration, inspect hook installation, check custom rules, and verify related command-line tools.
Why use it?
It helps locate setup problems that could stop AgentLint from checking a project correctly.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the agentlint plugin — 2 commands, 3 agents, 7 hooks, 1 MCP server shipped together

not rated 3 15d ago A scan 11 tokens original MIT
View the source file mauhpr/agentlint-plugin
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.

agentmods
npx agentmods add agents/mauhpr/agentlint-plugin/doctor
Clone the repo
git clone --depth 1 https://github.com/mauhpr/agentlint-plugin

Or install agentlint, the plugin that ships this one along with the rest of its 2 commands, 3 agents, 7 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.

agentmods badge for doctor

README.md
[![agentmods](https://agentmods.dev/badge/agents/mauhpr/agentlint-plugin/doctor.svg)](https://agentmods.dev/agents/mauhpr/agentlint-plugin/doctor)
Your own site
<a href="https://agentmods.dev/agents/mauhpr/agentlint-plugin/doctor"><img src="https://agentmods.dev/badge/agents/mauhpr/agentlint-plugin/doctor.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 474 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00011 $0.00474
Opus 5 $0.00005 $0.00237
Sonnet 5 $0.00002 $0.00095
Haiku 4.5 $0.00001 $0.00047

Measured 3d ago against content hash 5a866cbdcfc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

agents/doctor.md · 49 lines

What it actually says

You are a diagnostic agent for AgentLint configuration issues.

Steps

  1. Run diagnostics: Run agentlint doctor --project-dir "$CLAUDE_PROJECT_DIR" and display the results.

  2. Check configuration:

    • Read agentlint.yml and verify it has valid YAML syntax
    • Check that listed packs exist (universal, quality, python, frontend, react, seo, security, autopilot, or custom pack names)
    • Verify severity mode is valid (strict, standard, relaxed)
    • Warn about any unknown rule IDs in the rules section

  3. Check hook installation:

    • Read .claude/settings.json and verify agentlint hooks are registered
    • Check that PreToolUse, PostToolUse, and Stop hooks are present
    • Verify the agentlint command path resolves correctly

  4. Check custom rules:

    • If custom_rules_dir is set, verify the directory exists and has .py files
    • Check for orphaned packs (custom rules whose pack isn't in packs: list)
    • Verify custom rules load without errors

  5. Check CLI integration:

    • If cli-integration commands are configured, verify each binary exists in PATH
    • Check that timeout values are reasonable (warn if > 60s)

  6. Suggest improvements:

    • If no config exists, offer to run agentlint init
    • If hooks are missing, offer to run agentlint setup
    • Suggest optimal pack configuration based on project files
    • If an AGENTS.md file exists, suggest running agentlint import-agents-md
    • If project has .github/workflows/ or uses cloud CLIs, suggest autopilot pack

  7. Report status: Show a summary of AgentLint health with pass/fail for each check.

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. 3d ago First seen · 49 lines · 11 tokens per session scan A 5a866cbdcfc9

Subscribe to this mod's changes

doctor is an agent published in the GitHub repository mauhpr/agentlint-plugin (3 stars, last pushed 15d ago), licensed MIT. It adds 11 tokens to every session and 474 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.

DebuggingGuardrailsai-agentsclaude-codeclaude-code-pluginhookslinting
Related

Other agents, from other repositories

python-reviewer

Python code review agent — focuses on Python-specific issues: mutable default parameters, exception handling, type annotations.

majiayu000/vibeguard · 25 tokens

database-reviewer

Database review agent — reviews SQL/ORM code, migration scripts, query performance, data consistency.

majiayu000/vibeguard · 23 tokens

dispatcher

Optional read-only role selector used only when the user explicitly asks for agent dispatch.

majiayu000/vibeguard · 18 tokens

e2e-runner

End-to-end testing agent — writes and runs E2E tests to validate critical user processes.

majiayu000/vibeguard · 25 tokens

refactor-cleaner

Refactoring cleaning agent — eliminate duplicate code, simplify complex logic, improve code structure, and keep behavior unchanged.

majiayu000/vibeguard · 27 tokens

go-build-resolver

Go build repair agent — focuses on the quick repair of Go compilation errors, module dependencies, and CGO issues.

majiayu000/vibeguard · 28 tokens