advanced-code-review-plan

advanced-code-review-plan is a command for coding agents from axiomantic/spellbook. It costs 19 tokens per session (4,405 once invoked), scanned A, original, MIT.

A strategic planning step for an advanced code review. It identifies the files in scope, rates their risk, estimates the review effort, and orders the work by priority.

In plain words
What is it for?
Use it to plan a review, categorize files by risk, apply severity priorities, and create an ordered review list.
Why use it?
It gives the review a defined starting scope and directs attention first to higher-risk areas such as security, payments, and migrations.

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-plan
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-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/axiomantic/spellbook/advanced-code-review-plan.svg)](https://agentmods.dev/commands/axiomantic/spellbook/advanced-code-review-plan)
Your own site
<a href="https://agentmods.dev/commands/axiomantic/spellbook/advanced-code-review-plan"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/advanced-code-review-plan.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 4,405 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 $0.04405
Opus 5 $0.00010 $0.02202
Sonnet 5 $0.00004 $0.00881
Haiku 4.5 $0.00002 $0.00441

Measured 5d ago against content hash 4647bb933817, 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-plan 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 5d 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-plan.md · 470 lines

How it starts

The opening of the file, as written. The whole thing — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase 1: Strategic Planning

Invariant Principles

  1. Risk-based prioritization: Higher risk files are reviewed first. Security, payment, and migration files take precedence over tests and documentation.
  2. Scope clarity: All files in scope must be identified before review starts. No file should be discovered mid-review.
  3. Complexity honesty: Estimates must reflect actual review effort required. Underestimating leads to rushed reviews; overestimating wastes planning time.

Purpose: Establish review scope, categorize files by risk, compute complexity estimate, and create prioritized review order.

1.0 Constants and Configuration

These constants are established at planning time and consumed across every phase.

Severity Order

SEVERITY_ORDER = {
    "CRITICAL": 0, "HIGH": 1, "MEDIUM": 2, "LOW": 3, "NIT": 4, "QUESTION": 5, "PRAISE": 6
}

CRITICAL is reserved for security vulnerabilities, data loss, and production outages. Bugs are HIGH, never CRITICAL.

Configurable Thresholds

Threshold Default Consumer
STALENESS_DAYS 30 /advanced-code-review-context 2.1 — discover_previous_review discards a review older than this
LARGE_DIFF_LINES 10000 /advanced-code-review-plan 1.6.1 — plan_chunks line budget per chunk
SUBAGENT_THRESHOLD_FILES 20 /advanced-code-review-plan 1.6.1 — plan_chunks file count that triggers chunked dispatch
VERIFICATION_TIMEOUT_SEC 60 Phase 4 circuit breaker — verification exceeding this stops the run

Read the full file on GitHub · 470 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. 5d ago First seen · 470 lines · 19 tokens per session scan A 4647bb933817

Subscribe to this mod's changes

advanced-code-review-plan is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 4,405 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.