again

A command for running several code-review passes in sequence, with each pass seeing the changes made by earlier passes.

In plain words
What is it for?
Use it to review staged changes, a commit, a branch, or a file or directory, with options for pass count, automatic fixes, reviewer model, and a pass limit.
Why use it?
A single review can miss problems; repeated reviews with fresh context provide additional checks and can address serious findings between passes.

Command

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 commands/hartbrook/lookagain/again
Clone the repo
git clone --depth 1 https://github.com/HartBrook/lookagain
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,688 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 $0.00012 $0.01688
Opus 5 $0.00006 $0.00844
Sonnet 5 $0.00002 $0.00338
Haiku 4.5 $0.00001 $0.00169

Measured 2d ago against content hash 8c9b4987bb1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

again 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 2d 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/commands/again.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Iterative Code Review

You orchestrate sequential, multi-pass code review. Passes run one at a time with fixes applied between each so the next reviewer sees improved code.

Phase 0: Setup

Parse arguments

The user may pass key=value pairs after the command name. The raw argument string is:

$ARGUMENTS

If the argument string is empty or blank, the user provided no overrides — use all defaults. Parse key=value pairs from the string. For any key not provided, use the default.

Key Default Description
passes 3 Number of review passes to run
target staged What to review: staged, commit, branch, or a file/directory path
auto-fix true Automatically fix must_fix issues between passes (true or false)
model thorough Reviewer model: fast (haiku), balanced (sonnet), thorough (inherit)
max-passes 7 Maximum passes if must_fix issues persist

Log the resolved configuration so it is visible in the output:

Configuration:
  passes:     <resolved value>
  target:     <resolved value>
  auto-fix:   <resolved value>
  model:      <resolved value>
  max-passes: <resolved value>

Generate run ID

Generate a run ID: YYYY-MM-DDTHH-MM-SS. All output goes under .lookagain/<run-id>/.

Orchestrator role

Do NOT read the codebase yourself. You are the orchestrator — spawn reviewers, collect results, apply fixes, aggregate. Create a TodoWrite list with one item per pass plus aggregation. Mark items in_progress when starting and completed when done.

Resolve scope

Using the resolved target value, determine the scope instruction to pass to each reviewer:

Target value Scope instruction for reviewer
staged "scope: staged — review only staged changes"
commit "scope: commit — review the last commit"
branch "scope: branch — review all changes on this branch vs base"
Any path "scope: path — review files in <target>"

Read the full file on GitHub · 143 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. 2d ago First seen · 143 lines · 12 tokens per session scan A 8c9b4987bb1c

Subscribe to this mod's changes

again is a command published in the GitHub repository HartBrook/lookagain (10 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 1,688 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.