agentmods.dev

grokodex-critique

grokodex-critique is a skill for Claude Code from anlostsheep/grokodex. It costs 90 tokens per session (577 once invoked), scanned A, original, MIT.

A read-only review that challenges a software design or a set of local Git changes. It focuses on trade-offs, alternative approaches, risks, and ways the design could fail rather than editing the code.

In plain words
What is it for?
Use it to critique the current working-tree changes or a comparison with a base branch, assess maintainability, and identify better options or failure modes.
Why use it?
It gives you a second examination of the chosen approach before implementation or merging. This can reveal design problems that a line-by-line bug review may miss.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the grokodex plugin — 6 skills shipped together

not rated 2repo 1mo ago A scan 90 tokens original MIT

Good fit Use it to critique the current working-tree changes or a comparison with a base branch, assess maintainability, and identify better options or failure modes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anlostsheep/grokodex/grokodex-critique
View source ↗ anlostsheep/grokodex
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.

Any agent
npx skills add anlostsheep/grokodex --skill grokodex-critique
Clone the repo
git clone --depth 1 https://github.com/anlostsheep/grokodex

Made for: Claude Code.

Or install grokodex, the plugin that ships this one along with the rest of its 6 skills.

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 grokodex-critique

README.md
[![agentmods](https://agentmods.dev/badge/skills/anlostsheep/grokodex/grokodex-critique/github.svg)](https://agentmods.dev/skills/anlostsheep/grokodex/grokodex-critique)
Your own site
<a href="https://agentmods.dev/skills/anlostsheep/grokodex/grokodex-critique"><img src="https://agentmods.dev/badge/skills/anlostsheep/grokodex/grokodex-critique/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 grokodex-critique

Your own site · 80×15
<a href="https://agentmods.dev/skills/anlostsheep/grokodex/grokodex-critique"><img src="https://agentmods.dev/badge/skills/anlostsheep/grokodex/grokodex-critique.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 577 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 $0.00090 $0.00577
Opus 5 $0.00045 $0.00289
Sonnet 5 $0.00018 $0.00115
Haiku 4.5 $0.00009 $0.00058

Measured 11d ago against content hash 3e00a9f007dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

grokodex-critique 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 11d 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.

plugins/grokodex/skills/grokodex-critique/SKILL.md · 51 lines

What it actually says

Grokodex Critique

Read-only design challenge through Grokodex MCP. Does not modify the repo. Focuses on approach, tradeoffs, and failure modes — not a line-by-line defect hunt.

When to use

  • User asks to challenge the design, critique the approach, or "挑刺方案 / 有没有更好的做法"
  • Tradeoffs, alternatives, risks, and failure modes — no implementation
  • Not for defect-focused code review → grokodex-review
  • Not for apply fixes → grokodex-run

Tool preference

  1. Always call MCP grok_run with profile: "critique" (required).
  2. Forbidden: shell/grok for the critique task.
  3. Do not call grok_run without profile for a pure critique request.

Steps

  1. Determine scope: working tree (default) or user-specified base ref.
  2. Collect with host tools: git status, staged/unstaged diff, or git diff base...HEAD. For large diffs, summarize and include the most critical file hunks / design-relevant context.
  3. If there is nothing to critique, tell the user and stop (do not call MCP).
  4. Build prompt including: scope label, collected diff/context, critique axes (approach correctness, alternatives, risks, failure modes, maintainability at design level).
  5. Call:
grok_run
  prompt: <assembled>
  profile: critique
  # optional: cwd, model, host_thread_id, max_turns, timeout_ms
  1. Present text findings. Do not start editing in the same turn unless the user explicitly asks to fix — then switch to grokodex-run without profile.

Permissions

  • profile=critique forces read-only in the bridge. Do not try to pass danger-full-access to "critique harder".
  • If envelope permission.notes mention downgrade, you may mention critique stayed read-only.

Hard rules

  1. profile=critique required.
  2. MCP only — no shell grok.
  3. No auto-fix after critique.
  4. Host/skill collects git; bridge does not.
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. 11d ago First seen · 51 lines · 90 tokens per session scan A 3e00a9f007dc

Subscribe to this mod's changes

grokodex-critique is a skill published in the GitHub repository anlostsheep/grokodex (2 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 577 once invoked, about $0.0005 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 CodeCode reviewagentcodexgrokmcpplugin
Related

Other skills, from other repositories

ai-slop-cleaner

Use when a working code path feels bloated, noisy, or over-abstracted, when asked to clean up or deslop AI-generated code, or when a reviewer-only anti-slop pass is requested.

yeaight7/agent-powerups · 48 tokens

tri-model-review

Use when a request needs parallel external perspectives — combined backend and UI work, code review from multiple angles, or cross-validation where different models may disagree.

yeaight7/agent-powerups · 34 tokens

architecture-simplification

Use when a codebase carries over-engineered abstractions, unnecessary layers, or redundant logic that should be collapsed without changing behavior.

yeaight7/agent-powerups · 31 tokens

redteam-code-audit-detail-pack

Domain routing and boundary guidance for authorized source code security review, including dangerous function tracing, data-flow analysis, logic flaw detection, and dependency review. Use when a task belongs to the code audit domain and needs scope, evidence, pivot, or exit criteria.

Unclecheng-li/DeepSec · 59 tokens

open-code-review

Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…

alibaba/open-code-review · 98 tokens

continual-learning

Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…

langchain-ai/open-swe · 89 tokens