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 WatsonTsai/smart-brief --skill make-briefgit clone --depth 1 https://github.com/WatsonTsai/smart-briefWrote 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/watsontsai/smart-brief/make-brief)<a href="https://agentmods.dev/skills/watsontsai/smart-brief/make-brief"><img src="https://agentmods.dev/badge/skills/watsontsai/smart-brief/make-brief/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/watsontsai/smart-brief/make-brief"><img src="https://agentmods.dev/badge/skills/watsontsai/smart-brief/make-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.08425 |
| Opus 5 | $0.00000 | $0.04213 |
| Sonnet 5 | $0.00000 | $0.01685 |
| Haiku 4.5 | $0.00000 | $0.00843 |
Grade A, and why
make-brief 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 — 567 lines — stays where its author put it; the contents beside it link to each section on GitHub.
make-brief - HTML pages built to be understood and decided on
Why this skill exists
The same piece of work was once delivered twice.
The first version opened with the shortlist: four candidate designs for a data pipeline, a table of throughput and error-rate metrics, and a ranking. The reader's response was:
"I don't really follow. Give me fuller context so I understand what we are doing."
The second version opened with the mechanism instead: each nightly run reads from whichever replica is least loaded, replica lag differs between runs, so the row count you get depends on which replica answered - which means that without pinning a snapshot, a lag difference gets read as real growth in orders. Only after that did it reach the method, and only then the four candidates. The response was "this one is good."
The data in the two versions was identical. The only difference was whether the reader's prerequisite knowledge had been built first.
This skill makes the second version the default.
The page is written in the reader's language, not in the language of this file
This skill file, starter.html, and every example in them are written in English. That is the
language of the instructions. It is not a decision about the language of the page you produce.
Write the page in the language the reader will read it in - which in practice means the language the
user has been talking to you in. A page that follows every structural rule here and is written in a
language its reader has to translate has failed at the one thing the skill exists for.
The examples are here to show the shape of a sentence, not to supply its words. "Queue time" as an h2 is demonstrating that a heading names the thing under discussion and stops there; the opening paragraph beneath it is demonstrating that the argument starts from where the problem came from. Reproduce those shapes in the target language; do not carry the English across.
Three things get missed in that order, every time the output is not English:
What ships with it
3 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.
- 4d ago Changed · +79 lines 79880579a58b
- 8d ago First seen · 488 lines · 0 tokens per session scan A f7ac5c549dd3
make-brief is a skill published in the GitHub repository WatsonTsai/smart-brief (6 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 8,425 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 2026-08-31.
Other skills, from other repositories
better-auth
Skill for integrating Better Auth - comprehensive TypeScript authentication framework for Cloudflare D1, Next.js, Nuxt, and 15+ frameworks. Use when adding auth, encountering D1 adapter errors, or implementing OAuth/2FA/RBAC features.
aceternity-ui
100+ animated React components (Aceternity UI) for Next.js with Tailwind. Use for hero sections, parallax, 3D effects, or encountering animation, shadcn CLI integration errors.
cloudflare-durable-objects
Cloudflare Durable Objects for stateful coordination and real-time apps. Use for chat, multiplayer games, WebSocket hibernation, or encountering class export, migration, alarm errors.
cloudflare-workflows
Cloudflare Workflows for durable long-running execution. Use for multi-step workflows, retries, state persistence, or encountering NonRetryableError, execution failed errors.
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.
cloudflare-email-routing
Cloudflare Email Routing for receiving/sending emails via Workers. Use for email workers, forwarding, allowlists, or encountering Email Trigger errors, worker call failures, SPF issues.