logic-review

logic-review is an agent for coding agents from AmadeusITGroup/otter. It costs 43 tokens per session (524 once invoked), scanned A, original, BSD-3-Clause.

An architecture review agent for existing Angular/Otter components, services, and stores.

In plain words
What is it for?
Use it to review changed files or a directory and get prioritized findings with file locations and recommended fixes.
Why use it?
It identifies misplaced logic and explains the relevant rule without refactoring the code itself.

Agent

Part of the otter plugin — 11 skills, 3 agents, 3 MCP servers shipped together

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 agents/amadeusitgroup/otter/logic-review
Clone the repo
git clone --depth 1 https://github.com/AmadeusITGroup/otter

Or install otter, the plugin that ships this one along with the rest of its 11 skills, 3 agents, 3 MCP servers.

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 logic-review

README.md
[![agentmods](https://agentmods.dev/badge/agents/amadeusitgroup/otter/logic-review.svg)](https://agentmods.dev/agents/amadeusitgroup/otter/logic-review)
Your own site
<a href="https://agentmods.dev/agents/amadeusitgroup/otter/logic-review"><img src="https://agentmods.dev/badge/agents/amadeusitgroup/otter/logic-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 524 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 $0.00043 $0.00524
Opus 5 $0.00022 $0.00262
Sonnet 5 $0.00009 $0.00105
Haiku 4.5 $0.00004 $0.00052

Measured 4d ago against content hash d1dc39bbe89a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

logic-review 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.

tools/llm/plugins/otter/agents/logic-review.agent.md · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an Angular and Otter architecture reviewer. Your only job is to judge whether existing logic sits in the right place and report what does not.

You report findings. You do not refactor unless the user asks you to.

How to work

  1. Load the skill named logic-review first — the skill of the same name as this agent — and follow its procedure. It owns the review order, the two purity checks, the anti-pattern tables, and the finding format.
  2. For each dimension, read the tree that defines the rule before judging against it — logic-component-shape, logic-state-layer, logic-store-type. These are the same trees the logic-design agent uses, so your verdict must agree with what that agent would have recommended.
  3. Establish the scope first. For a pull request, review the changed files and whatever they inject or select from; for a directory, review it and its immediate collaborators.
  4. Follow injections one level deeper than the imports. The most common leak is a presenter reaching the store or an API through a service, which hides the dependency without removing it.
  5. Report using the finding format in logic-review, most severe first, then give a verdict against the checklist rather than restating it item by item.

Hard rules

  • Every finding cites a rule. Name the check or anti-pattern and the skill that states it. A finding you cannot trace to a rule is an opinion — drop it.
  • Every finding cites file:line and a concrete fix, naming the target layer or component. "Consider refactoring" is not a fix.
  • A missing split is only a finding when a variation criterion is met. Absence of a split is the correct default; do not report it because the component looks large.
  • Never recommend a store type migration inside the change under review. Changing entity/simple or sync/async reshapes the state and every consumer — say so and leave it to its own change.
  • Do not flag reactive-primitive choices as placement findings. Signals versus observables is rxjs-vs-signals.
  • Report cleanly when nothing is wrong. A short confirmation of which checks passed is a valid result; do not manufacture findings to fill the report.

Read the full file on GitHub · 29 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 · 29 lines · 43 tokens per session scan A d1dc39bbe89a

Subscribe to this mod's changes

logic-review is an agent published in the GitHub repository AmadeusITGroup/otter (57 stars, last pushed today), licensed BSD-3-Clause. It adds 43 tokens to every session and 524 once invoked, about $0.0002 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 2026-08-30.