code-review

A Claude Code plugin that adds project knowledge to each session. Claude Code is a coding assistant, and this plugin uses an OKF-based knowledge base to provide context about the project.

In plain words
What is it for?
Use it when Claude Code needs recurring background about a project, such as its documentation, decisions, or internal knowledge.
Why use it?
It helps the assistant start with relevant project information instead of relying only on the files and instructions supplied in the current session.

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/code-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 336 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 $0.00336
Opus 5 $0.00000 $0.00168
Sonnet 5 $0.00000 $0.00067
Haiku 4.5 $0.00000 $0.00034

Measured yesterday against content hash 98282e9fc3af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 yesterday.

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/code-review.md · 43 lines

What it actually says

Run a code review. User input: $ARGUMENTS

What this does

Launches two review agents in parallel: code-reviewer (bugs, security, correctness) and arch-reviewer (structure, duplication, bloat). No browser, no UX — code only.

Step 1: Determine scope

  • If $ARGUMENTS is empty → review unstaged changes. If no unstaged changes, review the last commit (HEAD~1..HEAD).
  • If $ARGUMENTS contains a scope (e.g., "staged changes", "commits since main", a commit range) → use that scope.

Step 2: Check scope size

Run git diff --stat (or git diff <range> --stat) to count files in scope.

  • ≤10 files → launch one code-reviewer + one arch-reviewer, both with full scope, in parallel.
  • >10 files → split changed files into chunks of ~5-7 files. Launch one code-reviewer per chunk + one arch-reviewer for the full scope, all in parallel.

The arch-reviewer always gets the full scope — it needs the big picture.

Step 3: Present results

Merge all reports into one. Deduplicate findings across agents. Order by severity (critical first).

## Code Review

**Scope:** {range} ({N files}, +X -Y)
**Verdict:** CLEAN | ISSUES FOUND

### Critical
...

### Warning
...

### Nit
...

### Architecture
...
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. yesterday First seen · 43 lines · 0 tokens per session scan A 98282e9fc3af

Subscribe to this mod's changes

code-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 336 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.