agentmods.dev

review-doctor

review-doctor is a command for Claude Code from Eivor79/ai-debate-plugin. It costs 25 tokens per session (536 once invoked), scanned A, original, MIT.

A diagnostic command for an automated Claude/Codex review workflow. It checks required programs, the project workspace, and whether workflow scripts are up to date.

In plain words
What is it for?
Checking PowerShell and assistant command-line tools, validating workspace freshness, and synchronizing outdated scripts and templates.
Why use it?
It explains why the review workflow may not start and can repair stale or missing workflow files when asked to fix them.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument; mentions Codex.

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 ai-debate plugin — 1 skill, 4 commands shipped together

not rated 1repo 2mo ago A scan 25 tokens original MIT

Good fit Checking PowerShell and assistant command-line tools, validating workspace freshness, and synchronizing outdated scripts and templates.

Compare 6 commands from other repositories ↓
View source ↗ Eivor79/ai-debate-plugin
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 Eivor79/ai-debate-plugin
Claude Code
/plugin install ai-debate

Made for: Claude Code.

Or install ai-debate, the plugin that ships this one along with the rest of its 1 skill, 4 commands.

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 review-doctor

README.md
[![agentmods](https://agentmods.dev/badge/commands/eivor79/ai-debate-plugin/review-doctor/github.svg)](https://agentmods.dev/commands/eivor79/ai-debate-plugin/review-doctor)
Your own site
<a href="https://agentmods.dev/commands/eivor79/ai-debate-plugin/review-doctor"><img src="https://agentmods.dev/badge/commands/eivor79/ai-debate-plugin/review-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 review-doctor

Your own site · 80×15
<a href="https://agentmods.dev/commands/eivor79/ai-debate-plugin/review-doctor"><img src="https://agentmods.dev/badge/commands/eivor79/ai-debate-plugin/review-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 536 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00536
Opus 5 $0.00013 $0.00268
Sonnet 5 $0.00005 $0.00107
Haiku 4.5 $0.00003 $0.00054

Measured 10d ago against content hash 890793e046f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

review-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 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.

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.

ai-debate/commands/review-doctor.md · 23 lines

What it actually says

Diagnose why the ai_debate workflow might not run, and (with --fix) repair what can be repaired automatically.

Target: $1 if provided, else the directory containing run_auto.ps1 (default llm_wiki/ai_debate).

Check and report each item as OK / WARN / FAIL with a one-line remedy:

  1. PowerShell engine — on Windows: powershell or pwsh available (OK either way). On macOS/Linux: pwsh must exist; if missing → FAIL with install hint (brew install --cask powershell / apt-get install powershell).
  2. claude CLI on PATH — required. FAIL if missing.
  3. codex CLI on PATH — optional: if missing → WARN "solo fallback active: claude executes codex rounds (provenance-marked)".
  4. Workspace — exists? If not → FAIL, remedy: /review-new <topic> scaffolds automatically.
  5. Workspace freshness — compare each workspace script (run_auto.ps1, wait_for_review.ps1, update_status.ps1, scan_queue.ps1) and _templates/* against ${CLAUDE_PLUGIN_ROOT}/scripts/ by content hash. Stale/missing files → WARN listing them.
    • With --fix: overwrite stale/missing scripts and templates from the plugin (workspace README.md is NEVER touched; topics/status.json/index.md/logs untouched). Report updated/unchanged per file, and remind that a running coordinator must be restarted to pick up new scripts.
  6. git — informational only: note git/non-git mode (both fully supported).
  7. Coordinator liveness — if any topic status.json holds a live lock_owner/lock_until in the future, or run_auto.log.jsonl was written in the last few minutes, note "coordinator appears active"; otherwise "not running — /review-new starts it automatically".
  8. Queue health — count topics by state; highlight any owner=human/blocked_reason items needing attention.

End with a one-line verdict: "ready" / "ready (solo mode)" / "needs attention: ".

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 · 23 lines · 25 tokens per session scan A 890793e046f7

Subscribe to this mod's changes

review-doctor is a command published in the GitHub repository Eivor79/ai-debate-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 536 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.

Claude CodeDebuggingadversarial-reviewai-agentsclaude-code-plugincodex
Related

Other commands, from other repositories

linkerd

Linkerd-specific diagnostics — mTLS verification, proxy injection issues, authorization policy debugging, traffic management, and multi-cluster connectivity problems.

nitinjain999/platform-skills · 30 tokens

debug

Systematic debugging with hypotheses and evidence gathering.

primeline-ai/evolving-lite · 8 tokens

ia-report-bug

Report a bug in the whetstone plugin.

iliaal/whetstone · 14 tokens

data-flow-analysis

Trace how data flows through the system from input to output.

sigistry/marketplace · 11 tokens

register-plugin-asset

A project command for adding a distributable command, agent, or agent skill to a plugin manifest, the file that lists what a plugin provides.

s977043/river-review · 28 tokens

duck-off

Turn off Rubber Duck mode and answer normally.

centsandcode/rubber-duck · 8 tokens