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-component-shapenpx skills add AmadeusITGroup/otter --skill logic-component-shapegit 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-component-shape)<a href="https://agentmods.dev/skills/amadeusitgroup/otter/logic-component-shape"><img src="https://agentmods.dev/badge/skills/amadeusitgroup/otter/logic-component-shape.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 | $0.00043 | $0.01984 |
| Opus 5 | $0.00022 | $0.00992 |
| Sonnet 5 | $0.00009 | $0.00397 |
| Haiku 4.5 | $0.00004 | $0.00198 |
Grade A, and why
logic-component-shape 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision tree — component shape
Returns: single component, or container + presenter, plus the componentStructure to generate and the componentType to declare.
Default to a single component. A split separates data and business-logic access from pure presentation, and the container/presenter documentation says a component interacting with external entities may be split — not that it must be.
Will something vary?
The split puts a seam between data access and presentation so one can vary without touching the other. It is worth its cost only when something on one side actually varies.
CRITERION A one data source, several UI flavours
dense table on desktop and stacked cards on mobile; an A/B variant; or a
presenter integrators swap or configure at runtime — through the CMS or
Otter's component replacement mechanism — which is just another flavour
supplied from outside, and needs the display half to be its own component
whose inputs and outputs are the contract
without the seam: the fetch is duplicated per variant, or the template
branches on display concerns
CRITERION B one UI flavour, several data sources
a passenger list rendered from a search result on one screen and from a
saved itinerary on another
without the seam: the presentation is copied, and the copies drift
IF A or B is true -> BRANCH A: container + presenter
ELSE -> BRANCH B: single component
Name what varies before splitting. If you cannot say which of data source, display, or integrator-supplied implementation will differ, there is nothing for the seam to absorb.
"The logic feels complex enough to separate" is not an additional criterion. Complexity alone is a human judgement call — see the split without variation stop-and-ask in logic-placement.
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 · 191 lines · 43 tokens per session scan A 269c98edb972
logic-component-shape is a skill published in the GitHub repository AmadeusITGroup/otter (57 stars, last pushed 6d ago), licensed BSD-3-Clause. It adds 43 tokens to every session and 1,984 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…
JavaScript Tooling
Development tools, linting, and testing for JavaScript projects.