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/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.
<a href="https://agentmods.dev/skills/amadeusitgroup/otter/logic-review"><img src="https://agentmods.dev/badge/skills/amadeusitgroup/otter/logic-review.svg" alt="Reviewed on agentmods" width="80" 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 5.5 | $0.00015 | $0.00652 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo ago First seen · 119 lines · 37 tokens per session scan A 10039036739f
logic-review is a skill published in the GitHub repository AmadeusITGroup/otter (59 stars, last pushed today), licensed BSD-3-Clause. It adds 37 tokens to every session and 1,630 once invoked, about $0.0001 per session on Opus 5.5. 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
agent-upkeep
Perform one small, scoped maintenance improvement to the Elements monorepo and open a single reviewable pull request. Use this skill for scheduled or unattended upkeep runs that improve unit test coverage for one file, fix one behavioral bug in one module, or move one off ESLint rule toward enforcement to reduce…
agent-dependencies
Perform one conservative dependency or toolchain upgrade in the Elements monorepo and open a validated pull request. Use for nightly or unattended dependency maintenance, outdated package checks, first-party actions/ GitHub Actions updates, and pinned mise tool updates. Use the github-dependabot skill instead when the…
agent-debug-ci
Investigate failed scheduled or nightly GitHub Actions runs on the default branch, determine whether the failure is reproducible and repository-owned, implement the smallest evidence-backed fix, validate it, and open a pull request. Use when a failed nightly CI event starts an agent, or when the standard CI or…
audit-ci
Run and analyze Elements cold CI performance profiles and propose evidence-backed build, test, lint, and dependency-graph improvements. Use whenever asked to profile or benchmark pnpm run ci, rerun ci:profile, create a CI performance audit, compare CI timings, find bottlenecks or the completion path, investigate a CI…
authoring-projects
Author a new standalone NVIDIA Elements workspace project containing a Lit component, including package files, the five test types, Wireit tasks, workspace and CI registration, metadata generation, documentation-site integration, dependency-lint configuration, and generated lock/notice files. Use when creating or…
audit-simplification
Audit an Elements project, directory, or component for mechanisms that may not need to exist, including redundant state, attribute reflection, forwarding indirection, lifecycle plumbing, per-instance allocations, and custom synchronization that duplicates browser or Lit behavior. Use when the user says code feels…