advanced-code-review-context

advanced-code-review-context is a command for coding agents from axiomantic/spellbook. It costs 19 tokens per session (4,255 once invoked), scanned A, original, MIT.

A code-review command for loading earlier review results, pull-request history, and author decisions before a new review. A pull request is a proposed code change shared for review, and offline mode uses the local branch when remote information is unavailable.

In plain words
What is it for?
Use it as the context-gathering phase of a code review, especially when reviewing a pull request or a local branch without remote access.
Why use it?
It prevents reviewers from repeating issues the author already declined and preserves context about how the code has changed. It can also identify items the author specifically asked to have checked again.

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/axiomantic/spellbook/advanced-code-review-context
Clone the repo
git clone --depth 1 https://github.com/axiomantic/spellbook

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 advanced-code-review-context

README.md
[![agentmods](https://agentmods.dev/badge/commands/axiomantic/spellbook/advanced-code-review-context.svg)](https://agentmods.dev/commands/axiomantic/spellbook/advanced-code-review-context)
Your own site
<a href="https://agentmods.dev/commands/axiomantic/spellbook/advanced-code-review-context"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/advanced-code-review-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,255 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 $0.00019 $0.04255
Opus 5 $0.00010 $0.02128
Sonnet 5 $0.00004 $0.00851
Haiku 4.5 $0.00002 $0.00426

Measured 4d ago against content hash 0bc8e301042b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

advanced-code-review-context 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 4d 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.

commands/advanced-code-review-context.md · 466 lines

How it starts

The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase 2: Context Analysis

Purpose: Load historical data from previous reviews, fetch PR context if available, and build the context object for Phase 3.

Invariant Principles

  1. Do not re-raise declined items. Declined items stay declined. Respect the author's explicit decision.
  2. Apply historical context to current review. Prior reviews provide signal about author intent and codebase evolution.
  3. Track re-check requests explicitly. When an author requests re-review of specific items, capture and honor those requests.

Offline Mode

Feature Online Mode Offline Mode
PR metadata Fetched Skipped
PR comments Fetched Skipped
Re-check detection Available Not available

Fallback Chain

gh pr view (remote PR) -> git diff (local branch only)

Git Commands (whole-review reference)

This table covers every phase of the review, not just Phase 2. It also serves PR analysis via the gh CLI.

Command Phase Usage
branch-context.sh json 1 Detect base, fetch, compute merge base, report provenance
branch-context.sh files-committed 1 Coverage-manifest file list, committed-only endpoint
branch-context.sh diff-committed 1, 3 Diff content, committed-only endpoint
branch-context.sh files 1 Coverage-manifest file list including working tree (pre-commit review only)
branch-context.sh diff 1, 3 Diff content including working tree (pre-commit review only)
git show 4 Verify file contents at SHA

Read the full file on GitHub · 466 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. 4d ago First seen · 466 lines · 19 tokens per session scan A 0bc8e301042b

Subscribe to this mod's changes

advanced-code-review-context is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 4,255 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.