code-review

A slash command that opens an interactive viewer for reviewing code changes, either on your computer or in a GitHub pull request. A pull request is a proposed change submitted for review before it is merged.

In plain words
What is it for?
Use it to review local changes, GitHub pull requests, or GitLab merge requests when the required command-line tools are available and authenticated.
Why use it?
It lets you inspect changed lines, add annotations, send feedback to the agent, or approve the review from a browser-based interface.

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/backnotprop/plannotator/code-review
Clone the repo
git clone --depth 1 https://github.com/backnotprop/plannotator
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 4,284 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 $0.00023 $0.04284
Opus 5 $0.00012 $0.02142
Sonnet 5 $0.00005 $0.00857
Haiku 4.5 $0.00002 $0.00428

Measured yesterday against content hash 2723b1701a52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 yesterday.

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.

apps/marketing/src/content/docs/commands/code-review.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The /plannotator-review command opens an interactive code review UI for your local changes or a GitHub pull request.

Usage

Review local changes:

/plannotator-review

Review a GitHub pull request:

/plannotator-review https://github.com/owner/repo/pull/123

PR review uses the gh CLI for authentication, so private repos work automatically if you're authenticated with gh auth login.

GitLab merge request URLs are also supported when the glab CLI is installed and authenticated.

How it works

Local review:

User runs /plannotator-review
        ↓
Agent runs: plannotator review
        ↓
the detected VCS provider captures changes
        ↓
Review server starts, opens browser with diff viewer
        ↓
User annotates code, provides feedback
        ↓
Send Feedback → feedback sent to agent
Approve → configured approval prompt sent to agent

PR review:

User runs /plannotator-review <github-url>
        ↓
Agent runs: plannotator review <github-url>
        ↓
gh CLI fetches PR diff and metadata
        ↓
Review server starts, opens browser with diff viewer
        ↓
User annotates code, provides feedback
        ↓
Send Feedback → PR context included in feedback
Approve → configured approval prompt sent to agent

Stacked PRs and MRs

When a PR or MR targets a non-default branch, Plannotator marks it as stacked in the review header. The default view remains Layer, which matches the platform diff and is the safe mode for posting inline review comments.

If Plannotator has a local checkout for the PR or MR, the header also offers Full stack. Full stack shows everything from the repository default branch through the current checked-out head, which helps you understand the whole chain before reviewing the current layer.

Platform posting is intentionally limited to Layer because GitHub and GitLab inline comments are anchored to the PR or MR's own diff. Use Full stack for comprehension and agent review, then switch back to Layer before posting to the platform.

Read the full file on GitHub · 269 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. yesterday First seen · 269 lines · 23 tokens per session scan A 2723b1701a52

Subscribe to this mod's changes

code-review is a command published in the GitHub repository backnotprop/plannotator (8,256 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 4,284 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.