A command that sends an adversarial code review through a chosen outside provider and model. Adversarial review means asking another model to challenge the current implementation and look for weaknesses.

Use it to challenge an implementation, select a review model, and inspect the resulting critique before accepting a change.

It gives you a second review perspective and helps expose problems the main coding model may have missed. If no model is specified, it helps choose one that is available.

review-with — Command for coding agents by pealmeida: A command that sends an adversarial code review through…

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/pealmeida/anymodel-plugin/review-with

Clone the repo

git clone --depth 1 https://github.com/pealmeida/anymodel-plugin

Or install anymodel, the plugin that ships this one along with the rest of its 11 commands, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/pealmeida/anymodel-plugin/review-with.svg)](https://agentmods.dev/commands/pealmeida/anymodel-plugin/review-with)

Your own site

<a href="https://agentmods.dev/commands/pealmeida/anymodel-plugin/review-with"><img src="https://agentmods.dev/badge/commands/pealmeida/anymodel-plugin/review-with.svg" alt="Measured on agentmods" 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 527 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.

Model	Per session	Once invoked
Fable 5	$0.00013	$0.00527
Opus 5	$0.00006	$0.00264
Sonnet 5	$0.00003	$0.00105
Haiku 4.5	$0.00001	$0.00053

Measured 3d ago against content hash fe293a450dd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-with 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 3d 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.

plugins/anymodel/commands/review-with.md · 48 lines

What it actually says

Run an adversarial review after helping the user choose the provider/model. This is the review-focused semantic chain for users who want a selected model to challenge the current implementation while the main CLI model orchestrates the command.

Raw user request: $ARGUMENTS

Selection rules:

If the request contains --model <provider/model>, preserve it and skip model selection.
If it contains a natural model token such as zai/glm-5.2, ollama/qwen3-coder, or opencode-go/kimi, convert that to --model <token>.
If it contains only a provider id, run:
```
node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" models --provider <provider> --json
```
Then ask the user to choose one reachable model returned for that provider.
If it contains no provider/model, run:
```
node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" models --json
```
Then ask the user to choose from up to three reachable <provider>/<model> options.
Ignore providers where ok is false or no models are returned.
If no reachable model exists, return the models output verbatim and tell the user to run /anymodel:setup.

Review rules:

Preserve runtime and review flags exactly: --engine, --base, --scope, --wait, --background, --cwd.
Preserve any focus text exactly after removing provider/model selector words.
This command is review-only. Do not fix issues, apply patches, or suggest that you are about to make changes.

Foreground dispatch:

node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" adversarial-review <final arguments>

Background dispatch:

If the final arguments include --background, launch the Bash command in the background and do not wait for completion.
Tell the user exactly: "AnyModel adversarial review started in the background. Check /anymodel:status for progress."

Return foreground stdout verbatim. Do not summarize, fix, or add commentary after the review.

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.

3d ago First seen · 48 lines · 13 tokens per session scan A fe293a450dd2

Subscribe to this mod's changes

review-with is a command published in the GitHub repository pealmeida/anymodel-plugin (0 stars, last pushed 26d ago), licensed Apache-2.0. It adds 13 tokens to every session and 527 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.

Code review adversarial-review ai-orchestration claude-code cli-tools llm-agents mcp-server

/commit-push

Commit and push all changes from this chat session using Conventional Commits.

DataCovey/nornweave · 18 tokens

/release

Release a new version — updates CHANGELOG, pyproject.toml, creates git tag, and pushes.

DataCovey/nornweave · 23 tokens

mega-approve

Approve the mega-plan and start feature execution. Creates worktrees and generates PRDs for each feature. Usage: /plan-cascade:mega-approve [--flow ] [--tdd ] [--confirm] [--no-confirm] [--spec ] [--first-principles] [--max-questions N] [--auto-prd] [--agent ] [--prd-agent ] [--impl-agent ].

Taoidle/plan-cascade · 110 tokens

auto

AI auto strategy executor. Analyzes task and automatically selects and executes the best strategy: direct execution, hybrid-auto PRD generation, hybrid-worktree isolated development, or mega-plan multi-feature orchestration.

Taoidle/plan-cascade · 41 tokens

hybrid-auto

Generate PRD from task description and enter review mode. Auto-generates user stories with priorities, dependencies, and acceptance criteria for parallel execution. Usage: /plan-cascade:hybrid-auto [--flow ] [--tdd ] [--confirm] [--no-confirm] [--spec ] [--first-principles] [--max-questions N] [--agent ]…

Taoidle/plan-cascade · 107 tokens

hybrid-worktree

Start a new task in an isolated Git worktree with Hybrid Ralph PRD mode. Creates worktree, branch, loads existing PRD or auto-generates from description. Usage: /plan-cascade:hybrid-worktree [--flow ] [--tdd ] [--confirm] [--no-confirm] [--spec ] [--first-principles] [--max-questions N] [--agent ] [design-doc-path].

Taoidle/plan-cascade · 125 tokens