full-review

A combined review command that checks code changes, project structure, the running web page, and user experience at once.

In plain words
What is it for?
Use it to inspect recent code changes, check a local app at http://localhost:5174, find structural issues, and receive one summary of the results.
Why use it?
It gathers several kinds of feedback in one run, so problems are less likely to be missed or reviewed separately.

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/rigos0/superturtle/full-review
Clone the repo
git clone --depth 1 https://github.com/Rigos0/superturtle

Made for: Claude Code.

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 381 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 $0.00381
Opus 5 $0.00000 $0.00191
Sonnet 5 $0.00000 $0.00076
Haiku 4.5 $0.00000 $0.00038

Measured 3d ago against content hash 15fbfbcb7dd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

full-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 3d 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.

.claude/commands/full-review.md · 45 lines

What it actually says

Run a full review — code, architecture, browser, and UX. User input: $ARGUMENTS

What this does

Launches all four review agents in parallel: code-reviewer, arch-reviewer, browser-tester, and ux-reviewer.

Agent prompts

  1. code-reviewer — Review unstaged changes. If there are no unstaged changes, review the last commit instead (HEAD~1..HEAD). Pass through any extra context from $ARGUMENTS.

  2. arch-reviewer — Same scope as code-reviewer. Review for duplication, bloat, missed reuse, and structural issues. Pass through any extra context.

  3. browser-tester — Navigate to http://localhost:5174, take a screenshot, check that the page renders without errors, and report console health. Pass through any extra context as specific checks.

  4. ux-reviewer — Navigate to http://localhost:5174, evaluate the current state of the app against UX/UI best practices, and return a design critique. Pass through any extra context to focus the review.

After agents return

Compile a single summary:

## Full Review Summary

### Code Review
**Verdict:** CLEAN | ISSUES FOUND
{Findings}

### Architecture Review
**Verdict:** CLEAN | ISSUES FOUND
{Findings}

### Browser Test
**Verdict:** PASS / FAIL
{Findings}

### UX Review
**Grade:** A / B / C / D
{Key issues}

### Action Items
{Numbered list of things to fix, ordered by severity — critical first}

If any agent fails to run (e.g., dev server not running), note it in the summary and still report results from the agents that succeeded.

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. 3d ago First seen · 45 lines · 0 tokens per session scan A 15fbfbcb7dd5

Subscribe to this mod's changes

full-review is a command published in the GitHub repository Rigos0/superturtle (123 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 381 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.