titanium-review

A command that reviews a codebase with separate agents for code quality, security, and testing, then combines their findings into one report.

In plain words
What is it for?
Use it for a broad code review that produces severity-based findings, practical recommendations, and a summary of security and testing issues.
Why use it?
It brings several kinds of review together so defects, vulnerabilities, and missing tests are easier to find and prioritise.

Command

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/webdevtodayjason/titanium-plugins/titanium-review
Clone the repo
git clone --depth 1 https://github.com/webdevtodayjason/titanium-plugins
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,698 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 $0.00006 $0.03698
Opus 5 $0.00003 $0.01849
Sonnet 5 $0.00001 $0.00740
Haiku 4.5 $0.00001 $0.00370

Measured 2d ago against content hash c74f10fdd1ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

titanium-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 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.

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/titanium-toolkit/commands/titanium-review.md · 693 lines

How it starts

The opening of the file, as written. The whole thing — 693 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Titanium Review Command

You are coordinating a comprehensive quality review of the codebase. This command launches multiple specialized review agents in parallel, aggregates their findings, and creates a detailed review report.

Orchestration Model: You launch 3 review agents simultaneously in separate context windows. Each agent has specialized skills and reviews from their domain expertise. They run in parallel for efficiency.

Review Agents & Their Skills:

  • @code-reviewer: code-quality-standards, security-checklist, testing-strategy
  • @security-scanner: security-checklist, code-quality-standards
  • @tdd-specialist: testing-strategy, code-quality-standards

Why Parallel: Review agents are independent - they don't need each other's results. Running in parallel saves 60-70% time compared to sequential reviews.

Overview

This review process:

  1. Identifies what code to review
  2. Launches 3 review agents in parallel (single message, multiple Task calls)
  3. Aggregates and categorizes findings from all agents
  4. Uses vibe-check for meta-review
  5. Creates comprehensive review report
  6. Stores findings in Pieces LTM
  7. Presents actionable summary with severity-based recommendations

Step 1: Identify Review Scope

Determine What to Review

Option A: Recent Changes (default)

git diff --name-only HEAD~1

Reviews files changed in last commit.

Option B: Current Branch Changes

git diff --name-only main...HEAD

Reviews all changes in current branch vs main.

Option C: Specific Files (if user specified)

# User might say: /titanium:review src/api/*.ts

Use the files/pattern user specified.

Option D: All Code (if user requested)

# Find all source files
find . -type f \( -name "*.ts" -o -name "*.js" -o -name "*.py" -o -name "*.rb" \) -not -path "*/node_modules/*" -not -path "*/venv/*"

Build File List

Create list of files to review. Store in memory for agent prompts.

Example:

Files to review:
- src/api/auth.ts
- src/middleware/jwt.ts
- src/routes/users.ts
- tests/api/auth.test.ts

Read the full file on GitHub · 693 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 · 693 lines · 6 tokens per session scan A c74f10fdd1ce

Subscribe to this mod's changes

titanium-review is a command published in the GitHub repository webdevtodayjason/titanium-plugins (7 stars, last pushed 7mo ago), licensed MIT. It adds 6 tokens to every session and 3,698 once invoked, about $0.0000 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 2026-08-31.