visionagent: Command for Claude Code

.claude/commands/review.md

review is a command for Claude Code from sijeeshmiziha/visionagent. It costs 0 tokens per session (522 once invoked), scanned A, original, MIT.

A command that performs a detailed review of code changes in the current Git branch or selected files. It checks types, correctness, architecture, error handling, and tests.

In plain words
What is it for?
Use it to review a branch, staged changes, a specific file, or a pull request; you can also pass a file path, PR number, or the word "staged".
Why use it?
It provides a consistent checklist for spotting defects, missing tests, unsafe async code, and integration problems before merging changes.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is sijeeshmiziha/visionagent's own configuration. It tells Claude Code how to work on visionagent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything visionagent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sijeeshmiziha/visionagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sijeeshmiziha/visionagent/main/.claude/commands/review.md
Clone the repo
git clone --depth 1 https://github.com/sijeeshmiziha/visionagent

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/sijeeshmiziha/visionagent/review.svg)](https://agentmods.dev/commands/sijeeshmiziha/visionagent/review)
Your own site
<a href="https://agentmods.dev/commands/sijeeshmiziha/visionagent/review"><img src="https://agentmods.dev/badge/commands/sijeeshmiziha/visionagent/review.svg" alt="Measured on agentmods" height="20"></a>
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 522 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 $0.00000 $0.00522
Opus 5 $0.00000 $0.00261
Sonnet 5 $0.00000 $0.00104
Haiku 4.5 $0.00000 $0.00052

Measured 8d ago against content hash d88114379842, 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 · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

Perform a thorough code review of changes in this branch.

Arguments

$ARGUMENTS (Optional: a specific file path, PR number, or "staged" for staged changes only)

Review Process

1. Identify Changes

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

Or if reviewing staged:

git diff --staged --name-only

2. Read Every Changed File

Read each changed file completely. Don't skim — understand the full context.

3. Review Checklist

Type Safety:

  • No any types in src/ (tests/examples may use them)
  • All public functions have explicit return types
  • Zod schemas match the actual data being validated
  • import type used for type-only imports

Correctness:

  • Error cases are handled (not silently swallowed)
  • Async/await used correctly (no floating promises)
  • No race conditions in agent execution loops
  • Edge cases covered (empty inputs, null/undefined, API errors)

Architecture:

  • New tools follow the ToolConfig pattern
  • New modules are exported through proper index.ts chain
  • No circular imports
  • New features are exported from src/index.ts if public API

Testing:

  • New functionality has corresponding tests in tests/
  • Tests use MSW mocks (not real API calls)
  • Tests cover happy path AND error cases
  • Coverage doesn't regress

Code Quality:

  • No dead code or unused imports
  • Consistent naming with existing codebase
  • No console.log left in production code (use logger)
  • Comments explain WHY, not WHAT

Documentation:

  • New public API documented in README.md
  • CHANGELOG.md updated
  • JSDoc on exported functions/interfaces

4. Security Check

  • No API keys or secrets hardcoded
  • No user input passed directly to shell commands
  • No path traversal vulnerabilities in file operations

5. Run Validation

npm run ci

6. Report

Provide:

  • Summary of what the change does
  • Issues found (if any) with file:line references
  • Suggested improvements
  • Overall verdict: APPROVE / REQUEST_CHANGES / NEEDS_DISCUSSION

Read the full file on GitHub · 91 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 · 91 lines · 0 tokens per session scan A d88114379842

Subscribe to this mod's changes

review is a command published in the GitHub repository sijeeshmiziha/visionagent (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 522 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 2026-08-31.