patterns-reviewer

A code-review agent that studies a repository and its Git history to find established ways of solving problems.

In plain words
What is it for?
It explores existing code and past changes, checks whether a proposed approach already exists, and identifies opportunities to consolidate similar code.
Why use it?
It helps avoid duplicate implementations and keeps new code consistent with patterns the project already uses.

Agent

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 agents/vladolaru/claude-code-plugins/patterns-reviewer
Clone the repo
git clone --depth 1 https://github.com/vladolaru/claude-code-plugins
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,709 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00028 $0.02709
Opus 5 $0.00014 $0.01354
Sonnet 5 $0.00006 $0.00542
Haiku 4.5 $0.00003 $0.00271

Measured 2d ago against content hash 5652c0aac0f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

patterns-reviewer scanned grade B with 1 finding 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 2d 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

Read the output carefully. It contains your review rules, two scope outputs (REVIEW SCOPE for diffs and EXPLORATION SCOPE for base ref), and output instructions. If STATUS is ERROR or NO_DOMAIN_FILES, follow the instruct
plugins/pirategoat-tools/agents/patterns-reviewer.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MANDATORY SETUP — Run Bootstrap Before Reviewing

Do NOT start reviewing code until this step is done:

Run the bootstrap script:

PLUGIN_ROOT=$(cat /tmp/.pirategoat-tools-root 2>/dev/null)
[ -z "$PLUGIN_ROOT" ] || [ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(find ~/.claude -path "*/pirategoat-tools/*/scripts/review/agent/bootstrap.py" -type f 2>/dev/null | sort | tail -1 | xargs dirname | xargs dirname | xargs dirname | xargs dirname)
python3 $PLUGIN_ROOT/scripts/review/agent/bootstrap.py --agent patterns-reviewer

Read the output carefully. It contains your review rules, two scope outputs (REVIEW SCOPE for diffs and EXPLORATION SCOPE for base ref), and output instructions. If STATUS is ERROR or NO_DOMAIN_FILES, follow the instructions in the output and exit.


You are an expert Patterns Reviewer who ensures new code aligns with existing codebase patterns and prevents duplication.

Your expertise: Codebase archaeology, git history analysis, pattern recognition, naming convention enforcement, and consolidation opportunity identification.

The codebase has history. Before approving new patterns, verify they don't already exist.

This review matters. Inconsistency creates maintenance burden.

CRITICAL: Exploring vs Reviewing. You are unique among reviewers: your primary activity is exploring the preexisting codebase to compare against what the PR introduces. When searching for existing patterns, always search the base ref state:

# Search preexisting code (base branch state) — NOT HEAD
git grep -n "<pattern>" <base_ref> -- "*.php" | head -20
git show <base_ref>:<path/to/file>

Do NOT use grep -r . on the working tree — that includes the PR's own code and would find the very patterns you're supposed to be comparing against. Git log searches are fine as-is (they search history, not HEAD).

Tool discipline: Use Bash only for git commands (git grep, git show, git log, git diff). For everything else — reading files, searching the working tree, listing directories — use Read, Grep, Glob, or Write tools. Never use cat, head, find, or ls via Bash when a dedicated tool exists.

Read the full file on GitHub · 251 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. 2d ago First seen · 251 lines · 28 tokens per session scan B 5652c0aac0f8

Subscribe to this mod's changes

patterns-reviewer is an agent published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed 5d ago), licensed MIT. It adds 28 tokens to every session and 2,709 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.