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.
npx skills add AmadeusITGroup/otter --skill logic-reviewgit clone --depth 1 https://github.com/AmadeusITGroup/otterWrote 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.
[](https://agentmods.dev/skills/amadeusitgroup/otter/logic-review)<a href="https://agentmods.dev/skills/amadeusitgroup/otter/logic-review"><img src="https://agentmods.dev/badge/skills/amadeusitgroup/otter/logic-review.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 15 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 5.1 | $0.00037 | $0.01630 |
| Opus 5 | $0.00018 | $0.00815 |
| Sonnet 5 | $0.00007 | $0.00326 |
| Haiku 4.5 | $0.00004 | $0.00163 |
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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Logic review — review mode
Assess code that already exists against the same trees the design side uses, so a review can never contradict a design recommendation.
To decide where something new should go, use logic-placement.
Procedure
Read in this order, and read the tree before judging its dimension — do not judge from memory.
| # | Look at | Read | Judge |
|---|---|---|---|
| 1 | Component classes, decorators, templates | logic-component-shape |
is the split, or its absence, justified; does componentType match the role |
| 2 | What each class injects and holds | logic-state-layer |
is the layer the shallowest one that works; are API calls in the right place |
| 3 | Store files, if any | logic-store-type |
does the variant match the data |
Rules for the whole pass:
- Judge a split by what varies, not by whether it exists. A missing split is a finding only when one of the variation criteria is met. An existing split whose container only forwards inputs is a finding regardless.
- Do not recommend a store type migration inside the change under review. See the store type migration stop-and-ask in
logic-placement.
Check — presenter purity
The test: can the presenter be rendered from a spec by supplying inputs only? If it needs a store or an HTTP mock, logic has leaked.
Follow the injections one level deeper than the imports. A presenter that injects no store and calls no HTTP client can still reach both through a service, which hides the dependency without removing it.
FOR each service a presenter injects:
does it select from the store, call an API, or trigger a side effect
beyond the component?
yes -> FINDING: the dependency belongs in the container
no -> allowed, if it is a presentation helper such as formatting or breakpoints
Check — componentType against the actual role
A mismatch between @O3rComponent({ componentType }) and what the class does is a reliable signal that logic sits in the wrong place.
Either the type or the logic must move — decide which from the responsibility table in logic-component-shape.
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.
- 8d ago First seen · 119 lines · 37 tokens per session scan A 10039036739f
logic-review is a skill published in the GitHub repository AmadeusITGroup/otter (58 stars, last pushed today), licensed BSD-3-Clause. It adds 37 tokens to every session and 1,630 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.
Other skills, from other repositories
aperture_lab_reviewer
Review Aperture Lab F-Stop offline review prompts and return JSON-only findings about title, summary, status, intentFrame, toolFamily, and consequence. Use when acting as the reviewer model inside the Aperture Lab F-Stop loop; do not edit code and do not return prose outside the required JSON.
code-quality-analysis
Analyze Angular / Cumulocity Web SDK code for anti-patterns, bugs, and quality issues. Use when reviewing components, services, or modules for code quality, maintainability, performance, and correctness. Covers TypeScript best practices, Angular idioms, C8Y SDK usage patterns, and project-specific conventions.…
igniteui-angular-linting
Quick-reference for linting the core Ignite UI for Angular library. Covers the combined lint command (lint:lib), ESLint for TypeScript and templates, and Stylelint for Sass/SCSS styles. Use when an agent needs to run the main linters, fix lint errors, or understand the primary lint configuration. Do NOT use for…
engineering-voice-ai-integration-engineer
A guide for building speech-to-text pipelines that turn recorded audio into cleaned transcripts and structured application data.
design-image-prompt-engineer
A prompt-writing specialist for photography and AI image generation. It turns visual ideas into detailed text descriptions for creating professional-looking photographs.
custom-openai-provider
Configure any OpenAI-compatible API as a Hermes model provider — NVIDIA NIM, Together AI, Fireworks, Groq, local vLLM/Ollama, or any custom endpoint. Covers the critical provider-clearing pitfall.