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 agentmods add skills/amadeusitgroup/otter/logic-state-layernpx skills add AmadeusITGroup/otter --skill logic-state-layergit 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-state-layer)<a href="https://agentmods.dev/skills/amadeusitgroup/otter/logic-state-layer"><img src="https://agentmods.dev/badge/skills/amadeusitgroup/otter/logic-state-layer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00048 | $0.01525 |
| Opus 5 | $0.00024 | $0.00763 |
| Sonnet 5 | $0.00010 | $0.00305 |
| Haiku 4.5 | $0.00005 | $0.00153 |
Grade A, and why
logic-state-layer 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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision tree — logic layer
Returns: component class, service (and its scope), or store.
Walk down and stop at the first match, except where a step tells you to read the next one before concluding. Each step down costs indirection, so earn it.
Step — component-local: does this state die with the component?
TRIGGER the state is scoped to one component and read by nothing else
local signals, derived values, event handlers, a form this component owns
RESULT component class
IMPLEMENT signal(), computed(), local form wiring — add no service for this
VERIFY nothing outside the component reads it
no service or store was created for it
STOP. The layer is decided.
// Search term and pagination are pure UI concerns: nothing outside this
// component reads them, so they need no service and no store.
public readonly searchTerm = signal('');
public readonly currentPage = signal(1);
public readonly displayedItems = computed(() =>
this.items().slice((this.currentPage() - 1) * this.pageSize(), this.currentPage() * this.pageSize())
);
Step — shared or stateless: is it reused beyond one component?
CRITERION A behaviour or state shared between components
CRITERION B stateless and reusable regardless of sharing — a wrapper over a browser
API, a pure computation, a cross-cutting concern such as logging
CRITERION C orchestration across several API calls, or reusable pre/post processing
IF none is true -> go to the application-scoped step
IF any is true -> a service covers it, but a store criterion can still apply on top.
Read the application-scoped step before concluding:
none of its criteria met -> RESULT: injectable service
any of its criteria met -> RESULT: store for the state, plus a
service only for what B or C describes
CHOOSE THE SCOPE (service only)
shared only between a container and its own subcomponents
-> providers: [] on that container
shared across unrelated features, and no store criterion applied
-> providedIn: 'root'
VERIFY the container injects it; a presenter does not, unless it is a pure
presentation helper
it does not select from the store — that selection belongs in the container
STOP once the application-scoped step has been read and returned no store.
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.
- 4d ago First seen · 160 lines · 48 tokens per session scan A 43eb9a349e85
logic-state-layer is a skill published in the GitHub repository AmadeusITGroup/otter (57 stars, last pushed today), licensed BSD-3-Clause. It adds 48 tokens to every session and 1,525 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
review-pending-pr-reviews
Review, grill, edit, and post pending PR review drafts saved by /review-pr (or its batch/cron runners). Lists drafts that have not yet been posted, walks the maintainer through each finding, then posts, closes, or discards. Use when the user says "post my pending reviews", "what reviews are waiting", "go through the…
chart
Use when the user asks to visualize data with charts, graphs, or plots using the chart tool (bar, line, scatter, pie, time series, etc.).
pr-review-triage
Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.
dependency-triage
Scan package manifests and lockfiles for outdated and vulnerable dependencies. Classify by severity and update type.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
implementation-readiness
Verify BRD-lite, PRD, SRS/FRS, UX, and test prerequisites before implementation starts.