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.
git clone --depth 1 https://github.com/jsgerman-oss/blackrim-nimbus-skillsWrote 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/commands/jsgerman-oss/blackrim-nimbus-skills/cf-scaffold-project)<a href="https://agentmods.dev/commands/jsgerman-oss/blackrim-nimbus-skills/cf-scaffold-project"><img src="https://agentmods.dev/badge/commands/jsgerman-oss/blackrim-nimbus-skills/cf-scaffold-project/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/commands/jsgerman-oss/blackrim-nimbus-skills/cf-scaffold-project"><img src="https://agentmods.dev/badge/commands/jsgerman-oss/blackrim-nimbus-skills/cf-scaffold-project.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 | $0.00037 | $0.02458 |
| Opus 5 | $0.00018 | $0.01229 |
| Sonnet 5 | $0.00007 | $0.00492 |
| Haiku 4.5 | $0.00004 | $0.00246 |
Grade A, and why
cf-scaffold-project 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 12d 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloudflare Scaffold Project
Scaffold a new Cloudflare project for a workload described as: $ARGUMENTS
What to do
-
Confirm the project type. Ask the user which template they want, with a one-line recommendation based on the workload description:
- Static site with optional edge logic → Pages (connect a GitHub repo; optional Pages Functions for API routes).
- API handler, proxy, or lightweight service → Worker (module syntax,
wrangler.toml, deployed via Wrangler). - Full-stack app with structured data and blob storage → Worker + D1 + R2 (Worker handles routing, D1 stores relational data, R2 stores user uploads or assets).
- Long-running or multi-step processes → Worker + Queues + Durable Objects (add Queues for background tasks and Durable Objects for coordination state).
Do not prescribe — recommend, then defer to the user.
-
Confirm scope with up to three questions if not obvious:
- Target Cloudflare account and zone (or
workers.devsubdomain only)? - Multi-environment (staging + production) or single environment?
- Greenfield, or migrating an existing app (import existing data, bind to existing resources)?
- Target Cloudflare account and zone (or
-
Generate the project skeleton in the current working directory (or a subdirectory the user picks). Every scaffold must include:
wrangler.toml(orwrangler.jsonc) with per-environment stanzas.package.jsonwithwranglerpinned in devDependencies;npm run dev,npm run deploy, andnpm testscripts.- TypeScript configuration (
tsconfig.json) with@cloudflare/workers-typesfor type safety. .gitignorecoveringnode_modules/,.dev.vars,dist/,.wrangler/..dev.vars(local secrets file) — empty template with a comment; confirm it is already in.gitignore.- A
README.mdwith setup, local dev, deploy, and environment variable instructions. - Terraform skeleton in
infra/for Cloudflare resources managed outside Wrangler. - GitHub Actions workflow(s) in
.github/workflows/. - At least one unit test (
vitestwith@cloudflare/vitest-pool-workers) confirming the scaffold is testable.
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.
- 12d ago First seen · 284 lines · 37 tokens per session scan A 9696f58ddf15
cf-scaffold-project is a command published in the GitHub repository jsgerman-oss/blackrim-nimbus-skills (8 stars, last pushed 26d ago), licensed MIT. It adds 37 tokens to every session and 2,458 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 2026-08-31.
Other commands, from other repositories
devops
Designs CI/CD pipelines, infrastructure, observability, and deployment strategy. Use when preparing platform readiness for a feature.
otel-forward
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
platform
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
monitors
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
load-balancer
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
up
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.