plan-critique

A command for testing a written development plan from an adversarial point of view before it is approved.

In plain words
What is it for?
Use it for red-team review, pre-mortems, falsification, or steelmanning of a plan; its findings are intended for a separate plan-revision step.
Why use it?
It exposes assumptions, risks, and ways the plan could fail while there is still time to revise it.

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/xonovex/platform/plan-critique
Clone the repo
git clone --depth 1 https://github.com/xonovex/platform
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 303 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 $0.00021 $0.00303
Opus 5 $0.00010 $0.00151
Sonnet 5 $0.00004 $0.00061
Haiku 4.5 $0.00002 $0.00030

Measured 2d ago against content hash baa33cd26498, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-critique 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.

packages/command/command-workflow/commands/plan-critique.md · 30 lines

What it actually says

/xonovex-workflow:plan-critique - Adversarially Critique a Plan

Lifecycle: research → decide → create → revise ⇄ critique → accept → subplans-create → continue → update → validate

Arguments

  • plan-file (optional): Path to the plan document (auto-detects from git config or the most recent plan in plans/).
  • --mode <mode> (optional): Which adversarial lens(es) to run: red-team, pre-mortem, falsify, steelman, or all. Default: red-team + pre-mortem.

Delegation

Load the plan-guide skill (plugin xonovex-skill-plan) and perform its critique operation with these arguments. Run this as a fresh session / independent agent that did not author the plan. Self-critique defends instead of attacks. The skill is the source of truth for the procedure, output format, and gotchas. Do not restate them.

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 · 30 lines · 21 tokens per session scan A baa33cd26498

Subscribe to this mod's changes

plan-critique is a command published in the GitHub repository xonovex/platform (5 stars, last pushed 3d ago), licensed MIT. It adds 21 tokens to every session and 303 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.