review-with-fresh-eyes

review-with-fresh-eyes is a command for Claude Code from liortesta/ClawdAgent. It costs 0 tokens per session (365 once invoked), scanned A, original, Apache-2.0.

A code-review command that gives a new subagent only the finished changes, tests, and project rules. The reviewer has no access to the original implementation discussion.

In plain words
What is it for?
Use it after making code changes to receive an independent review, a quality rating, and specific fixes when the result has important problems.
Why use it?
A reviewer without the author’s reasoning can spot bugs, edge cases, security problems, and design smells that the author may overlook. It reduces the effect of becoming attached to the original approach.

Command for Claude Code

Written for Claude Code: context: fork in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents.

Good fit Use it after making code changes to receive an independent review, a quality rating, and specific fixes when the result has important problems.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/liortesta/clawdagent/review-with-fresh-eyes
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/liortesta/ClawdAgent

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-with-fresh-eyes

README.md
[![agentmods](https://agentmods.dev/badge/commands/liortesta/clawdagent/review-with-fresh-eyes/github.svg)](https://agentmods.dev/commands/liortesta/clawdagent/review-with-fresh-eyes)
Your own site
<a href="https://agentmods.dev/commands/liortesta/clawdagent/review-with-fresh-eyes"><img src="https://agentmods.dev/badge/commands/liortesta/clawdagent/review-with-fresh-eyes/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.

agentmods 80×15 button for review-with-fresh-eyes

Your own site · 80×15
<a href="https://agentmods.dev/commands/liortesta/clawdagent/review-with-fresh-eyes"><img src="https://agentmods.dev/badge/commands/liortesta/clawdagent/review-with-fresh-eyes.svg" alt="Reviewed on agentmods" width="80" 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 365 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 $0.00365
Opus 5 $0.00000 $0.00182
Sonnet 5 $0.00000 $0.00073
Haiku 4.5 $0.00000 $0.00036

Measured 11d ago against content hash 53ca6f3ae27f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-with-fresh-eyes 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 11d 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-with-fresh-eyes.md · 57 lines

What it actually says

Fresh-Eyes Code Review

Spawn a NEW subagent with clean context to review the code changes. The reviewer MUST NOT see the original implementation discussion — only the final code.

Process:

  1. Identify all changed files (git diff)
  2. Spawn a subagent with ONLY the following context:
    • The changed files (final version)
    • The test files (if any)
    • The CLAUDE.md project rules
    • NO conversation history, NO implementation reasoning
  3. The reviewer should:
    • Read the code as if seeing it for the first time
    • Check for bugs, logic errors, and edge cases
    • Check for security issues
    • Check for anti-patterns and code smells
    • Rate quality 1-10
    • Try to "break" the code mentally — think of inputs that would cause failures
  4. If rating is below 7 — list specific issues that need fixing
  5. If rating is 7+ — approve with any minor suggestions

Why Fresh Eyes?

The developer (or Claude) who wrote the code has anchoring bias — they're mentally committed to their approach. A fresh reviewer with no context will catch things the author is blind to.

Output Format:

## Fresh-Eyes Review

**Reviewer Context**: Clean (no implementation history)
**Files Reviewed**: [list]

### Quality Rating: X/10

### Bugs Found
- [bug with file:line reference]

### Security Issues
- [issue with severity]

### Anti-Patterns
- [pattern with suggestion]

### Breaking Scenarios
- [input/scenario that could cause failure]

### Verdict: APPROVE / REQUEST CHANGES

$ARGUMENTS

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. 11d ago First seen · 57 lines · 0 tokens per session scan A 53ca6f3ae27f

Subscribe to this mod's changes

review-with-fresh-eyes is a command published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 15d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 365 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 2026-08-30.