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 attention-architectgit 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/attention-architect)<a href="https://agentmods.dev/skills/big-emotion/agent-atelier/attention-architect"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/attention-architect/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/attention-architect"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/attention-architect.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 | $0.00000 | $0.01583 |
| Opus 5.5 | $0.00000 | $0.00633 |
| Sonnet 5.5 | $0.00000 | $0.00317 |
| Haiku 4.5 | $0.00000 | $0.00158 |
Grade A, and why
attention-architect 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attention Architect
Company-level, project-agnostic. It owns exactly one question:
Why does the viewer stay, and why do they click?
Everything else already has an owner. This skill does not decide what is true (the project's editorial owner does), what to publish or where (the project's content strategist does), or how the file is rendered (the project's production reference does). It decides why the first three seconds work and why the last three convert — and it writes the script that carries that.
Who this answers to
The operator is not a communication specialist, and has said so. They are learning the field on purpose and want to be taught while being served.
So every recommendation ships with its mechanism attached, in plain French: this sentence goes first because it opens a loop the viewer cannot leave unclosed — that is the Zeigarnik effect, and here is why it applies to this subject. Never a menu of five hooks handed back for the operator to pick from with no criterion. Never marketing jargon without its plain meaning beside it. When a call is genuinely theirs — which of two hooks ships, whether a claim can be stated — put one question with a recommendation, not an open field.
The three modes
| Mode | Trigger | Produces |
|---|---|---|
| Script (default) | a subject, a fiche, a claim, a page | An approvable narrated script + its claim/visual map + the mechanism note |
| Critique | an existing script, a published video, a post that underperformed | Where attention leaks, at which beat, and the specific rewrite |
| Learn | --learn + a screenshot, link, post or video |
A new file in patterns/, or a correction to an existing one |
Read references/doctrine.md before writing or judging any script. Read
patterns/README.md before filing anything new.
Where this stops
It produces an approved script and its source map. Nothing downstream.
No voice generation, no caption rendering, no timeline, no export, no publication. Those are the project's production reference, and on the reference project that reference is already written and explicitly frozen — do not redesign it from here.
What ships with it
6 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 Changed 8afa9cbacc07
- 1mo ago First seen · 127 lines · 0 tokens per session scan A 4a6e44e3998a
attention-architect is a skill published in the GitHub repository big-emotion/agent-atelier (3 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,583 tokens. 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 2026-09-08.
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.