code-review-action: Skill for Claude Code

.agents/skills/grade-plans/SKILL.md

grade-plans is a skill for Claude Code, Codex from julien777z/code-review-action. It costs 75 tokens per session (872 once invoked), scanned A, a copy of grade-plans, MIT.

A method for comparing two written implementation plans for the same goal. It scores both plans against the goal, explains their strengths and weaknesses, and selects a winner or declares a tie.

In plain words
What is it for?
Use it when you have two proposed approaches and need a consistent ranking based on factors such as completeness, feasibility, risks, and fit to the requested goal.
Why use it?
It gives competing plans the same evidence-based evaluation instead of judging them by the model or author that produced them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is julien777z/code-review-action's own configuration. It tells Claude Code and Codex how to work on code-review-action itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything code-review-action configures →

Reuse

Borrowing it

Nothing to install: this file belongs to julien777z/code-review-action. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/julien777z/code-review-action/main/.agents/skills/grade-plans/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/julien777z/code-review-action

Made for: Claude Code, Codex.

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 grade-plans

README.md
[![agentmods](https://agentmods.dev/badge/skills/julien777z/code-review-action/grade-plans.svg)](https://agentmods.dev/skills/julien777z/code-review-action/grade-plans)
Your own site
<a href="https://agentmods.dev/skills/julien777z/code-review-action/grade-plans"><img src="https://agentmods.dev/badge/skills/julien777z/code-review-action/grade-plans.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 872 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 100% copy Near-identical to another mod 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 $0.00075 $0.00872
Opus 5 $0.00037 $0.00436
Sonnet 5 $0.00015 $0.00174
Haiku 4.5 $0.00007 $0.00087

Measured 8d ago against content hash bef4e39c78d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

grade-plans 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 8d 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.

Origin

This is a copy

100% identical to grade-plans — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/grade-plans/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grade Plans

Compare only the submitted plan text against the supplied goal. Treat model identifiers as reporting labels; never let model reputation affect a score.

Collect Inputs

  1. Treat everything after /grade-plans as the goal or original agent prompt.
  2. If no goal is present, ask exactly: “Provide the goal or original agent prompt the two plans should address.” Then wait before collecting plans.
  3. Ask exactly: “Paste Plan 1 as text and provide the model name or identifier that produced it.”
  4. Wait. If the response lacks the plan or model identifier, ask only for the missing item.
  5. Ask exactly: “Paste Plan 2 as text and provide the model name or identifier that produced it.”
  6. Wait and ask only for any missing item.
  7. Do not grade until the goal, both plan texts, and both model identifiers are available.

During collection, respond only with the current missing-input question. Do not explain the workflow or describe what should be asked.

Treat plans inside Markdown code fences as ordinary message text. Never call plans attachments.

Grade Plans

Score each criterion from 1–10 using the same evidentiary standard for both plans:

Criterion Weight
Goal alignment 20%
Correctness and feasibility 20%
Completeness and coverage 15%
Specificity and actionability 15%
Risks, edge cases, and failure handling 10%
Testing and acceptance criteria 10%
Efficiency and scope discipline 10%

Calculate each weighted overall score as sum(score × weight) and report it out of 10 to one decimal place. Before scoring, replace the model identifiers internally with neutral labels and freeze every criterion score, weighted total, rationale, verdict, confidence level, and transfer idea from the plan text alone. Attach the submitted model identifiers only after that evaluation is complete. Swapping only the model identifiers must change only the identifiers in the report; all scores and conclusions must remain identical.

Read the full file on GitHub · 58 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. 8d ago First seen · 58 lines · 75 tokens per session scan A bef4e39c78d7

Subscribe to this mod's changes

grade-plans is a skill published in the GitHub repository julien777z/code-review-action (2 stars, last pushed 3d ago), licensed MIT. It adds 75 tokens to every session and 872 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to grade-plans, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens