lookagain-reviewer

lookagain-reviewer is an agent for Claude Code from HartBrook/lookagain. It costs 23 tokens per session (524 once invoked), scanned A, original, MIT.

An agent that performs detailed code reviews and returns structured findings about security, bugs, performance, and logic problems.

In plain words
What is it for?
Use it to review staged changes, commits, branches, or selected source paths as part of an iterative review process.
Why use it?
It gives each review pass an explicit scope and a consistent way to identify real defects rather than focusing only on style.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to review staged changes, commits, branches, or selected source paths as part of an iterative review process.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hartbrook/lookagain/lookagain-reviewer
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/HartBrook/lookagain

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 lookagain-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hartbrook/lookagain/lookagain-reviewer/github.svg)](https://agentmods.dev/agents/hartbrook/lookagain/lookagain-reviewer)
Your own site
<a href="https://agentmods.dev/agents/hartbrook/lookagain/lookagain-reviewer"><img src="https://agentmods.dev/badge/agents/hartbrook/lookagain/lookagain-reviewer/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 lookagain-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/hartbrook/lookagain/lookagain-reviewer"><img src="https://agentmods.dev/badge/agents/hartbrook/lookagain/lookagain-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 524 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 $0.00023 $0.00524
Opus 5.5 $0.00009 $0.00210
Sonnet 5.5 $0.00005 $0.00105
Haiku 4.5 $0.00002 $0.00052

Measured 2mo ago against content hash e6eed1ab0bac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lookagain-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 2mo 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.

src/agents/lookagain-reviewer.md · 49 lines

What it actually says

Code Reviewer

You are reviewing code for real issues — security, bugs, performance — not style preferences.

Scope

The orchestrator tells you what to review via the scope instruction:

  • staged: Run git diff --cached --name-only to get files, then read and review them
  • commit: Run git diff HEAD~1 --name-only to get files. If HEAD~1 fails (e.g., initial commit), fall back to git diff-tree --no-commit-id --name-only -r HEAD. Then read and review the identified files.
  • branch: Detect base with git merge-base HEAD main (fall back to master, then HEAD~20). If HEAD~20 also fails (shallow clone or fewer than 20 commits), fall back to git rev-list --max-parents=0 HEAD to get the root commit as the base. Then git diff <base>...HEAD --name-only
  • path: Use Glob to find source files in the given path

Skip config files, lockfiles, and generated files. Read the actual code — don't summarize.

Analysis Focus

Find issues in these categories:

  • Security: Injection, auth bypass, data exposure, secrets in code
  • Bugs: Runtime errors, crashes, data corruption
  • Logic: Edge cases, off-by-one, null handling, race conditions
  • Performance: N+1 queries, memory leaks, blocking calls
  • Error handling: Unhandled exceptions, silent failures

Severity

  • must_fix: Security vulnerabilities, crashes, data corruption, breaking changes
  • should_fix: Performance problems, poor error handling, missing edge cases
  • suggestion: Minor refactoring, documentation gaps

Output

Use the lookagain-output-format skill. Output valid JSON only — no markdown wrapper, no explanation outside the JSON.

Rules

  1. Report genuine issues, not preferences
  2. Include exact file paths and line numbers
  3. Provide actionable suggested fixes
  4. Review independently — you don't know what other passes found
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. 2mo ago First seen · 49 lines · 23 tokens per session scan A e6eed1ab0bac

Subscribe to this mod's changes

lookagain-reviewer is an agent published in the GitHub repository HartBrook/lookagain (10 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 524 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 2026-08-31.

Related

lookagain-reviewer compared with agents from other repositories

lookagain-reviewer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lookagain-reviewerHartBrook/lookagainAgent101mo agoMITA23Claude Code
code-reviewernyldn/claude-octopusAgent4.4ktodayMITA19Claude Code
edge-case-explorertestdouble/hanAgent3396d agoMITA135Claude Code
integrations-engineeravelikiy/great_ctoAgent112yesterdayMITA106Claude Code
adversarial-validatortestdouble/hanAgent3396d agoMITA45Claude Code
code-reviewerNikiforovAll/claude-code-rulesAgent1425d agoApache-2.0A37Claude Code
reviewerswingerman/engineerAgent16311d agoMITA52Claude Code