code-reviewer

A checklist-based reviewer for TypeScript changes in the babysitter monorepo, a repository containing multiple related packages. It checks types, asynchronous code, errors, package boundaries, SDK conventions, compatibility, and tests.

In plain words
What is it for?
Use it to review TypeScript changes for unsafe types, incorrect imports, dependency problems, weak error handling, broken public APIs, and missing or unhelpful tests.
Why use it?
It catches inconsistencies that may be missed when reviewing one package in isolation. It also checks that changes follow shared monorepo and SDK rules.

Agent for Claude Code

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/a5c-ai/babysitter/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter

Made for: Claude Code.

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 500 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 $0.00024 $0.00500
Opus 5 $0.00012 $0.00250
Sonnet 5 $0.00005 $0.00100
Haiku 4.5 $0.00002 $0.00050

Measured 3d ago against content hash f1a534ed3eef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-reviewer 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 3d 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/agents/code-reviewer.md · 77 lines

What it actually says

Code Reviewer

Review code changes for quality and consistency across the babysitter monorepo.

Review Checklist

TypeScript Quality

  • No any type escapes (use unknown if needed, then narrow)
  • Proper async/await usage (no floating promises)
  • Error handling with typed errors
  • Null checks before dereferencing
  • Proper use of optional chaining (?.) and nullish coalescing (??)

Monorepo Consistency

  • Imports use workspace package names (@a5c-ai/babysitter-sdk) not relative paths across packages
  • Shared types are in appropriate package
  • No circular dependencies between packages
  • Package boundaries respected

SDK Patterns

  • CLI commands follow existing patterns in packages/babysitter-sdk/src/cli/
  • Exported APIs are properly typed and documented
  • Backwards compatibility maintained for public APIs
  • Event sourcing patterns followed for state changes

Error Handling

  • Errors have meaningful messages
  • Async errors properly caught/propagated
  • User-facing errors are actionable
  • Internal errors logged appropriately

Testing

  • New functionality has tests
  • Tests are meaningful (not just coverage)
  • Mocks are minimal and focused
  • Test file naming matches source files

Review Process

  1. Get changed files:

    git diff --name-only HEAD~1
    
  2. For each TypeScript file, check:

    • Type safety
    • Error handling
    • Pattern consistency with similar files
  3. Cross-package changes: Verify imports and boundaries

  4. Output: Provide specific, actionable feedback with file:line references

Output Format

## Code Review: [Brief Summary]

### Issues Found

#### [Severity: High/Medium/Low] [Category]
**File**: `path/to/file.ts:42`
**Issue**: Description of the problem
**Suggestion**: How to fix it

### Recommendations
- General improvement suggestions

### Approved
- What looks good
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. 3d ago First seen · 77 lines · 24 tokens per session scan A f1a534ed3eef

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository a5c-ai/babysitter (1,757 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 500 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 2026-08-30.

Related

Other agents, from other repositories

typescript-expert

Expert in TypeScript specializing in type safety, async patterns, and modern ES features. Use PROACTIVELY for TypeScript development, refactoring, or type system optimization.

BlackBeltTechnology/pi-agent-dashboard · 35 tokens

java-style

How to write and shape Java code in this repository: formatting, language-feature use, complexity and reuse tradeoffs, and exception handling. Static-analysis tooling has its own page; see References.

martin-francois/symphony-trello · 0 tokens

rn-code-reviewer

Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…

Lykhoyda/rn-dev-agent · 234 tokens

implementer

Use when the implementation plan needs to be executed slice by slice. A seasoned coding expert that reads the plan, follows TDD discipline, executes one vertical slice at a time, and commits each slice atomically when its tests pass. Dispatched during the Implement phase.

bostonaholic/team · 56 tokens

questioner

Use as the first agent of the QRSPI pipeline. Decomposes a user's task description into a full task record (task.md) and neutral research questions (questions.md), plus conditional artifacts — a prd.md when the PRD criteria apply, and a repos.md listing the repos the topic touches when the description names more than…

bostonaholic/team · 89 tokens

test-architect

Use after the worktree is prepared to write all failing acceptance tests from the structure. Tests form the immutable scope fence for implementation. Operates inside the implement phase as a sub-step before the implementer runs.

bostonaholic/team · 46 tokens