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.
git clone --depth 1 https://github.com/ThrownLemon/claude-code-pluginsWrote 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.
[](https://agentmods.dev/commands/thrownlemon/claude-code-plugins/scan)<a href="https://agentmods.dev/commands/thrownlemon/claude-code-plugins/scan"><img src="https://agentmods.dev/badge/commands/thrownlemon/claude-code-plugins/scan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/thrownlemon/claude-code-plugins/scan"><img src="https://agentmods.dev/badge/commands/thrownlemon/claude-code-plugins/scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00013 | $0.00797 |
| Opus 5.5 | $0.00005 | $0.00319 |
| Sonnet 5.5 | $0.00003 | $0.00159 |
| Haiku 4.5 | $0.00001 | $0.00080 |
Grade A, and why
scan 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-AI Code Review Scan
Run a comprehensive code review of the entire project using multiple AI CLIs in parallel, then compare their findings.
What This Does
- Validates Prerequisites - Checks which CLIs are installed
- Analyzes Project - Identifies project structure and files
- Runs Parallel Reviews - Executes Claude, Gemini, and Codex in tmux split panes
- Watch in Real-Time - Opens a new terminal tab to view all CLIs working
- Aggregates Findings - Matches similar issues across reviewers
- Generates Comparison - Shows consensus, majority, and unique findings
Arguments
| Argument | Default | Description |
|---|---|---|
--clis |
claude,gemini,codex |
Which CLIs to use (any combination) |
--focus |
all |
Review focus area |
--exclude |
.gitignore patterns |
Additional patterns to exclude |
--timeout |
10 |
Minutes per CLI (max: 30) |
--mode |
tmux |
Execution mode: tmux (visual) or background (headless) |
Focus Areas
- all - Comprehensive review (security, quality, architecture, performance, best practices)
- security - Security vulnerabilities, injection risks, auth issues
- quality - Code readability, maintainability, DRY violations
- architecture - Design patterns, coupling, cohesion
- performance - Efficiency, memory, database queries
Examples
# Full review with all CLIs (opens tmux in new terminal)
/multi-ai-review:scan
# Security-focused review
/multi-ai-review:scan --focus security
# Use only Claude and Gemini
/multi-ai-review:scan --clis claude,gemini
# Exclude test files, longer timeout
/multi-ai-review:scan --exclude "test/**,__tests__/**" --timeout 15
# Run in background (headless, no tmux)
/multi-ai-review:scan --mode background
Tmux Mode (Default)
By default, reviews run in a tmux session with split panes so you can watch all CLIs simultaneously:
- A new terminal tab opens automatically
- Each CLI runs in its own pane
- Use
Ctrl+Bthenzto zoom a pane - Use
Ctrl+BthenDto detach (reviews continue) - Output is saved to
~/.multi-ai-review/<review-id>/
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.
- 1mo ago First seen · 90 lines · 13 tokens per session scan A 14b7d6e90960
scan is a command published in the GitHub repository ThrownLemon/claude-code-plugins (2 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 797 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
refactor
Systematic code refactoring with smart scope detection.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.