review-intent

review-intent is a command for Claude Code from davistroy/claude-marketplace. It costs 12 tokens per session (3,934 once invoked), scanned A, original, MIT.

A read-only project analysis that reconstructs what the software was originally meant to do and compares that goal with the current implementation. It uses project documents and can also inspect Git history, which records earlier changes.

In plain words
What is it for?
Use it to review the repository or a specific path, optionally include deeper Git-history analysis, and save the findings to a report.
Why use it?
It reveals scope drift, abandoned features, unfinished work, and differences between the planned product and the code that exists now.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions Claude Code.

Part of the personal-plugin plugin — 29 skills, 23 commands, 10 agents, 2 hooks shipped together

Good fit Use it to review the repository or a specific path, optionally include deeper Git-history analysis, and save the findings to a report.

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

Or install personal-plugin, the plugin that ships this one along with the rest of its 29 skills, 23 commands, 10 agents, 2 hooks.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/review-intent"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/review-intent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,934 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 $0.00012 $0.03934
Opus 5 $0.00006 $0.01967
Sonnet 5 $0.00002 $0.00787
Haiku 4.5 $0.00001 $0.00393

Measured 8d ago against content hash 069f763e0d6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-intent 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.

plugins/personal-plugin/commands/review-intent.md · 427 lines

How it starts

The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Intent

Perform a systematic analysis of what this project was originally intended to do versus what it currently does. This command reconstructs the original vision from project artifacts (README, docs, early commits, architecture decisions, specs) and compares it against the actual implementation to surface scope drift, abandoned features, unfinished work, and misaligned implementations. This is a read-only analysis — no files are modified.

Input Validation

Optional Arguments:

  • <path> - Specific file, directory, or subproject to analyze (default: repository root)
  • --deep - Include git history analysis for intent reconstruction (slower but more thorough)
  • --save - Save the report to a file instead of only displaying in conversation

Argument Detection: Check if the user provided a file path or directory as an argument ($ARGUMENTS). If provided, scope the review to that path only. If not provided, review the entire project from the repository root.

# Examples of argument detection:
/review-intent                     → Review entire project
/review-intent src/api             → Review only src/api directory
/review-intent --deep              → Review entire project with git history
/review-intent src/api --deep      → Review src/api with git history
/review-intent --save              → Review entire project, save report to file
/review-intent src/api --save      → Review src/api, save report to file

Validation: Before proceeding, verify:

  • This is a code project with sufficient history to infer intent (not an empty repo or single-file script)
  • If a specific path was provided, verify it exists and is not empty
  • Project has at least one of: README, docs directory, CLAUDE.md, specification files, meaningful commit messages, or architecture decision records
  • If no intent artifacts exist, report this early rather than guessing

If the project lacks intent signals:

Unable to determine project intent.

No intent artifacts found. This command requires at least one of:
  - README.md or similar documentation
  - Specification or requirements documents (PRD, BRD, TDD)
  - Architecture decision records (ADRs)
  - CLAUDE.md or similar project instructions
  - Meaningful commit history (not just "initial commit")
  - Issue tracker references or project boards

Suggestion: Create a README describing the project's purpose, then re-run.

Read the full file on GitHub · 427 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 · 427 lines · 12 tokens per session scan A 069f763e0d6e

Subscribe to this mod's changes

review-intent is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 3,934 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 2026-09-04.