project_review

project_review is a command for Claude Code from Helmi/claude-simone. It costs 0 tokens per session (2,399 once invoked), scanned A, original, MIT.

A command for reviewing an entire software project at a high level. It examines the project’s tests, documentation, progress, architecture, file organization, workflow, and technical decisions.

In plain words
What is it for?
Use it for a full project review or for a specified focus area, such as a milestone, sprint, architecture component, test setup, or implementation quality.
Why use it?
It brings scattered project risks and inconsistencies into one structured assessment. The required review areas help reveal problems that a review of only recent code changes may miss.

Command for Claude Code

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.

agentmods
npx agentmods add commands/helmi/claude-simone/project_review
Clone the repo
git clone --depth 1 https://github.com/Helmi/claude-simone

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 project_review

README.md
[![agentmods](https://agentmods.dev/badge/commands/helmi/claude-simone/project_review.svg)](https://agentmods.dev/commands/helmi/claude-simone/project_review)
Your own site
<a href="https://agentmods.dev/commands/helmi/claude-simone/project_review"><img src="https://agentmods.dev/badge/commands/helmi/claude-simone/project_review.svg" alt="Measured on agentmods" 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 2,399 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.02399
Opus 5 $0.00000 $0.01200
Sonnet 5 $0.00000 $0.00480
Haiku 4.5 $0.00000 $0.00240

Measured 5d ago against content hash 11f540bf0753, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project_review 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 5d 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

Copies of this mod

1 near-identical copy found in the catalogue:

legacy/.claude/commands/simone/project_review.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Review - Execute top to bottom

Perform a comprehensive project-level review focusing on architecture, progress, and technical decisions.

IMPORTANT:

  • This is a high-level review of overall project state, not recent changes.
  • Unless clearly mentioned in project documents, there is no timeline and schedule is irrelevant

Create a TODO with EXACTLY these 9 Items

  1. Analyze review scope and timing
  2. Execute and assess test infrastructure health
  3. Assess project documentation alignment
  4. Review milestone and sprint progress
  5. Analyze codebase architecture and structure
  6. Audit file organization and workflow compliance
  7. Evaluate technical decisions and complexity
  8. Critique implementation quality (John Carmack perspective)
  9. Provide comprehensive assessment with recommendations

Follow step by step and adhere closely to the following instructions for each step.

DETAILS on every TODO item

1. Analyze review scope and timing

Check: <$ARGUMENTS>

If empty, perform full project review. Otherwise interpret <$ARGUMENTS> to identify specific focus areas (milestone, sprint, architecture component, etc.). Unless stated in Argument do not compare to previews project reviews in .simone/10_STATE_OF_PROJECT.

IMPORTANT: This review looks at overall project state in context of recent changes.

CRITICAL: Read .simone/00_PROJECT_MANIFEST.md FIRST to understand:

  • Current milestone and sprint status
  • What work is complete vs in-progress vs planned
  • Active sprint objectives and deliverables

CONTEXT CHECK: Before evaluating functionality:

  • Navigate to .simone/03_SPRINTS/ to find the current sprint
  • Read the sprint meta file to understand what's in scope
  • Check completed vs planned tasks within the sprint
  • Understand what future sprints will deliver

REVIEW PRINCIPLE: Evaluate against CURRENT SPRINT deliverables, not full milestone scope.

2. Execute and assess test infrastructure health

CRITICAL: Test infrastructure health is a BLOCKING criteria for sprint/milestone progression.

Read the full file on GitHub · 262 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. 5d ago First seen · 262 lines · 0 tokens per session scan A 11f540bf0753

Subscribe to this mod's changes

project_review is a command published in the GitHub repository Helmi/claude-simone (558 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,399 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 2026-08-30.