review-intent.eval

review-intent.eval is a command for Claude Code from davistroy/claude-marketplace. It costs 0 tokens per session (495 once invoked), scanned A, original, MIT.

A command that compares a project's intended behavior, as described in documentation and design files, with what the current code actually does.

In plain words
What is it for?
Use it to inspect files such as README.md, CLAUDE.md, architecture documents, plugin metadata, commands, and skills, then produce a comparison report without changing files.
Why use it?
It makes differences between the plan and the implementation easier to find, including missing, outdated, or unclear parts.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions CLAUDE.md.

Good fit Use it to inspect files such as README.md, CLAUDE.md, architecture documents, plugin metadata, commands, and skills, then produce a comparison report without changing files.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/davistroy/claude-marketplace/review-intent.eval
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.

Clone the repo
git clone --depth 1 https://github.com/davistroy/claude-marketplace

Made for: Claude Code.

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-intent.eval

README.md
[![agentmods](https://agentmods.dev/badge/commands/davistroy/claude-marketplace/review-intent.eval/github.svg)](https://agentmods.dev/commands/davistroy/claude-marketplace/review-intent.eval)
Your own site
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/review-intent.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/review-intent.eval/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-intent.eval

Your own site · 80×15
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/review-intent.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/review-intent.eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 495 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 $0.00000 $0.00495
Opus 5 $0.00000 $0.00247
Sonnet 5 $0.00000 $0.00099
Haiku 4.5 $0.00000 $0.00049

Measured 11d ago against content hash f9f62028ca88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

review-intent.eval 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.

evals/commands/review-intent.eval.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eval: /review-intent

Purpose

Determines the original project intent from documentation and design artifacts, then compares it against the current implementation to identify discrepancies. Good output: a clear statement of intended behavior versus actual behavior, with specific gaps called out.

Fixtures

Fixture Purpose
docs/sample-prd.md Intent reference document for comparison

Test Scenarios

S1: Repo with CLAUDE.md and plugin docs as intent sources

Invocation: /review-intent

Must:

  • Reads intent sources (CLAUDE.md, README.md, plugin.json descriptions)
  • Reads current implementation (command files, skill files)
  • Produces a comparison report in conversation
  • Lists at least one area where implementation matches intent (positive finding)
  • Lists at least one area where implementation diverges or is unclear
  • No files created

Should:

  • Notes that deprecated/ commands are not in the active command list (intent vs reality)
  • Notes if any command in CLAUDE.md's command list is missing from the actual files
  • Organizes findings by severity or impact

Must NOT:

  • Modify any files
  • Fabricate discrepancies that don't exist

S2: With explicit requirements document

Invocation: /review-intent fixtures/docs/sample-prd.md

Must:

  • Uses sample-prd.md as the primary intent document
  • Compares PRD requirements against what exists in the current codebase
  • Notes that the PRD describes a Slack bot, and the current repo is a Claude plugin marketplace (clear discrepancy — good test of honesty)

Must NOT:

  • Pretend the repo matches the PRD when it clearly does not

S3: Read-only behavior

Must:

  • Does not create files
  • Does not make git commits

Rubric

Criterion Pass Threshold
Intent sources identified and cited Required
Both matching and diverging areas identified Required
No files created or modified Required
Does not fabricate discrepancies Required

Read the full file on GitHub · 72 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. 11d ago First seen · 72 lines · 0 tokens per session scan A f9f62028ca88

Subscribe to this mod's changes

review-intent.eval is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 495 tokens. 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.