review-plan-behavior

review-plan-behavior is a command for Claude Code from axiomantic/spellbook. It costs 13 tokens per session (838 once invoked), scanned A, original, MIT.

A checklist for verifying that an implementation plan describes existing code accurately. It requires source locations, real method signatures, confirmed behavior, and known constraints.

In plain words
What is it for?
Use it to inspect code references, validate method behavior, identify unsafe assumptions, and prepare instructions for agents that will implement the plan.
Why use it?
It stops plans from treating guesses about method names or parameters as facts. That prevents fabricated solutions that fail during implementation and lead to wasted debugging.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to inspect code references, validate method behavior, identify unsafe assumptions, and prepare instructions for agents that will implement the plan.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/axiomantic/spellbook/review-plan-behavior
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/axiomantic/spellbook

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 review-plan-behavior

README.md
[![agentmods](https://agentmods.dev/badge/commands/axiomantic/spellbook/review-plan-behavior/github.svg)](https://agentmods.dev/commands/axiomantic/spellbook/review-plan-behavior)
Your own site
<a href="https://agentmods.dev/commands/axiomantic/spellbook/review-plan-behavior"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/review-plan-behavior/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 review-plan-behavior

Your own site · 80×15
<a href="https://agentmods.dev/commands/axiomantic/spellbook/review-plan-behavior"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/review-plan-behavior.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 838 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 $0.00013 $0.00838
Opus 5 $0.00006 $0.00419
Sonnet 5 $0.00003 $0.00168
Haiku 4.5 $0.00001 $0.00084

Measured 5d ago against content hash 6ecdcc22f214, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-plan-behavior 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/review-plan-behavior.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase 3: Behavior Verification Audit

Invariant Principles

  1. Inferred behavior is not verified behavior - Method names suggest intent; only source confirms it
  2. Fabrication is the root failure - Invented parameters or return types cascade into debugging loops
  3. Every code reference needs file:line - Plans citing existing code without source location are unverified

The Fabrication Anti-Pattern

# FORBIDDEN: The Fabrication Loop
1. Plan assumes method does X based on name
2. Agent writes code, fails because method actually does Y
3. Agent INVENTS parameter: method(..., partial=True)
4. Fails because parameter doesn't exist
5. Agent enters debugging loop, never reads source
6. Hours wasted on fabricated solutions

# REQUIRED in Plan
1. "Behavior verified by reading [file:line]"
2. Actual method signatures from source
3. Constraints discovered from reading source
4. Executing agents follow verified behavior, no guessing

Dangerous Assumption Patterns

Flag when plan exhibits any of:

1. Assumes convenience parameters exist:

  • "Pass partial=True to allow partial matching" (VERIFY THIS EXISTS)
  • "Use strict_mode=False to relax validation" (VERIFY THIS EXISTS)

2. Assumes flexible behavior from strict interfaces:

  • "The test context allows partial assertions" (VERIFY: many require exhaustive assertions)
  • "The validator accepts subset of fields" (VERIFY: many require complete objects)

3. Assumes library behavior from method names:

  • "The update() method will merge fields" (VERIFY: might replace entirely)
  • "The validate() method returns errors" (VERIFY: might raise exceptions)

Read the full file on GitHub · 97 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 · 97 lines · 13 tokens per session scan A 6ecdcc22f214

Subscribe to this mod's changes

review-plan-behavior is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 838 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 2026-09-03.