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 big-emotion/agent-atelier --skill structure-carouselgit clone --depth 1 https://github.com/big-emotion/agent-atelierWrote 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/big-emotion/agent-atelier/structure-carousel)<a href="https://agentmods.dev/skills/big-emotion/agent-atelier/structure-carousel"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/structure-carousel/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/big-emotion/agent-atelier/structure-carousel"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/structure-carousel.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00125 | $0.01388 |
| Opus 5.5 | $0.00050 | $0.00555 |
| Sonnet 5.5 | $0.00025 | $0.00278 |
| Haiku 4.5 | $0.00013 | $0.00139 |
Grade A, and why
structure-carousel 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 10d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structure (carousel)
Headings are fixed. Section headings are fixed identifiers: copy them exactly as written in the deliverable templates (English, with the same hash marks), whatever the language of the profile. Only the text under a heading is written in the profile's language.
Turns idea.md and idea.json into everything the render step needs. It writes
words and picks image titles; it does not render, redesign a layout or read
a licence.
idea.md + idea.json → structure-carousel → cards.json, captions.md, sources.md,
images.json, citations.json → produce
Two ways to run it
- Interactive: show every title, body and source in deck order and ask for approval of the complete text before calling the step done.
- Studio (
project/studio.mdexists): the contract wins. Never ask, never block, write only the five files, and list every decision under## Choix faits pour toiincaptions.md.
What you read first
inputs/idea.mdandinputs/idea.json: the question, the angle, the promise, what the piece will not say, the sources, the reservations. Consume the subject report; do not choose a fresh argument. A card that cannot be written from the sources goes back to the idea step as a reservation; it is never padded with an invented source, date or image. Whenidea.jsoncarries aplan, it is the skeleton: one card per plan step, in its order, each card built on the sources of its step (the plan's steps are 4 to 9, as is a deck). Depart from it only with a reason in## Choix faits pour toi.beforeWritinglists what the idea step could not verify: no card states a claim that depends on it. Without a plan, build the deck from the report as before.project/profile.md: language, audience, the networks and the register of each.- On a revision:
revision.mdandinputs/previous/. Change what is asked, keep the rest, return every file in full.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 108 lines · 125 tokens per session scan A 1d33c021b632
structure-carousel is a skill published in the GitHub repository big-emotion/agent-atelier (3 stars, last pushed 2d ago), licensed MIT. It adds 125 tokens to every session and 1,388 once invoked, about $0.0005 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 2026-10-05.
Other skills, from other repositories
add-azuredevops
Adds Azure DevOps connector to a Power Apps code app. Use when querying work items, creating bugs, managing pipelines, or making ADO API calls.
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
ci-fixer
A CI job fails on a named revision and the fix belongs in code, config or tests, not in the CI provider.
push-ci
Push to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh CLI. Use when: user says 'push', 'push and watch CI', 'ship it', 'push-ci'. Not for: committing (use /smart-commit), creating PRs (use /create-pr), merging (use /merge-prep).
azure-devops
Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check…
cloudflare-workers-ci-cd
Complete CI/CD guide for Cloudflare Workers using GitHub Actions and GitLab CI. Use for automated testing, deployment pipelines, preview environments, secrets management, or encountering deployment failures, workflow errors, environment configuration issues.