review

review is a command for Claude Code from ncssm-robotics/ftc-claude. It costs 11 tokens per session (1,017 once invoked), scanned A, original, MIT.

A local review command that runs the same checks as the project’s pull-request bot.

In plain words
What is it for?
Run /review with an FTC skill name to perform all checks, or limit the review to code, security, or youth-safety checks.
Why use it?
It lets developers find code, security, and youth-content issues before opening a pull request.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Run /review with an FTC skill name to perform all checks, or limit the review to code, security, or youth-safety checks.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ncssm-robotics/ftc-claude/review
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.

Clone the repo
git clone --depth 1 https://github.com/ncssm-robotics/ftc-claude

Made for: Claude Code.

Wrote 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.

agentmods badge for review

README.md
[![agentmods](https://agentmods.dev/badge/commands/ncssm-robotics/ftc-claude/review.svg)](https://agentmods.dev/commands/ncssm-robotics/ftc-claude/review)
Your own site
<a href="https://agentmods.dev/commands/ncssm-robotics/ftc-claude/review"><img src="https://agentmods.dev/badge/commands/ncssm-robotics/ftc-claude/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,017 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00011 $0.01017
Opus 5 $0.00005 $0.00508
Sonnet 5 $0.00002 $0.00203
Haiku 4.5 $0.00001 $0.00102

Measured 8d ago against content hash 87582542af18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 8d 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/review.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Command

Runs the same code review checks locally that the PR bot runs, giving you feedback before submitting a PR.

Usage

/review <skill-name> [--type code|security|youth]

Arguments:

  • skill-name: Name of the skill to review (must exist in plugins/)
  • --type: Optional filter to run only specific review type(s)

Type Options

Flag Reviews Run
(none) All reviews (code + security + youth)
--type code Code quality and structure only
--type security Security checks only
--type youth Content appropriateness only

Examples

/review pinpoint                  # Run all reviews
/review pedro-pathing --type code # Code review only
/review decode --type security    # Security review only

Process

When this command is invoked:

  1. Validate the skill exists

    • Check plugins/<skill-name>/ directory exists
  2. Load review skills

    • Load code-review skill (unless filtered out)
    • Load security-review skill (unless filtered out)
    • Load youth-safety-review skill (unless filtered out)
  3. Execute checks

    • Run each check defined in the loaded review skills
    • Categorize results as pass (✓), warning (⚠), or error (✗)
  4. Output structured report

    • Show results grouped by review type
    • Include pass/warn/fail counts per type
    • Show overall summary

Output Format

Reviewing skill: pinpoint

=== Code Review ===
Structure:
  ✓ plugin.json exists and valid
  ✓ SKILL.md exists with frontmatter
  ✓ Name matches across files
  ✓ CHANGELOG.md exists with [Unreleased] section
Content Quality:
  ✓ Description includes WHAT and WHEN
  ✓ Under 500 lines (127 lines)
  ✓ Has Quick Start section
  ⚠ Missing Anti-Patterns section
  ✓ Has code examples
Marketplace:
  ✓ Listed in marketplace.json
  ✓ Version matches plugin.json
Code Review: 9/10 passed (1 warning)

=== Security Review ===
Credentials:
  ✓ No hardcoded API keys
  ✓ No hardcoded passwords
  ✓ No WiFi credentials
Configuration:
  ✓ Allowed FTC IPs only (192.168.43.1)
  ✓ No absolute paths
  ✓ No path traversal patterns
Code Injection:
  ✓ No eval/exec of user input
  ✓ No unsanitized shell commands
Security Review: 8/8 passed

=== Youth Safety Review ===
Language:
  ✓ No profanity detected
  ✓ Variable names appropriate
  ⚠ "killer_shot" may be flagged - verify context
Personal Info:
  ✓ No student names
  ✓ No school names
Content:
  ✓ Examples use neutral naming
Youth Safety Review: 4/5 passed (1 warning)

=== Summary ===
Code Review:     9/10  (1 warning)
Security Review: 8/8   (passed)
Youth Safety:    4/5   (1 warning)

Overall: PASSED with 2 warnings

Read the full file on GitHub · 157 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. 8d ago First seen · 157 lines · 11 tokens per session scan A 87582542af18

Subscribe to this mod's changes

review is a command published in the GitHub repository ncssm-robotics/ftc-claude (4 stars, last pushed 7mo ago), licensed MIT. It adds 11 tokens to every session and 1,017 once invoked, about $0.0001 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.