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/christopherlouet/claude-baseWrote 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/christopherlouet/claude-base/ops-serverless)<a href="https://agentmods.dev/commands/christopherlouet/claude-base/ops-serverless"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/ops-serverless/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/christopherlouet/claude-base/ops-serverless"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/ops-serverless.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 | $0.00548 |
| Opus 5.5 | $0.00000 | $0.00219 |
| Sonnet 5.5 | $0.00000 | $0.00110 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
ops-serverless 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 15d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SERVERLESS Agent
Deployment of serverless applications (AWS Lambda, Vercel, Cloudflare Workers).
Request context
$ARGUMENTS
Objective
Design and deploy a serverless architecture suited to the project, with cold start optimization and CI/CD integration.
Workflow
- Analyze the needs and choose the platform (AWS Lambda, Vercel, Cloudflare Workers)
- Structure the project (handlers, lib, types)
- Configure the framework (Serverless Framework, Vercel, Wrangler)
- Implement the handlers with error handling
- Optimize for cold starts (pooled connections, bundling, provisioned concurrency)
- Configure the deployment (local dev, staging, production)
- Estimate costs
Expected output
- Architecture serverless with platform justification
- Configuration (serverless.yml, vercel.json, wrangler.toml)
- Handlers implemented with suitable patterns
- Cost estimate monthly
Related agents
| Agent | Usage |
|---|---|
/ops:ops-ci |
Serverless CI/CD |
/ops:ops-monitoring |
Observability |
/ops:ops-cost |
Cloud cost optimization (FinOps) |
IMPORTANT: Optimize for cold starts - avoid heavy imports.
IMPORTANT: Use pooled database connections.
YOU MUST configure timeouts and memory according to the use case.
NEVER store state in memory - functions are ephemeral.
See also
Vendor skills for depth, by platform (recipe: docs/recipes/recommended-vendor-skills.md §"Stack-specific"):
- AWS Lambda —
awslabs/agent-pluginsplugins/aws-serverless/skills/*(Apache-2.0, plugin1.3.0at pine32b05b5): Lambda, SAM/CDK deployment, API Gateway, Step Functions, durable functions. Choose between: the plugin adds a hook after every Edit/Write (it runssam validate --linton SAM templates) and an MCP server run asuvx awslabs.aws-serverless-mcp-server@latest --allow-write(unpinned, write access); the skill folders alone avoid both, and the skills then ask before working without their MCP tools. - Cloudflare Workers —
cloudflare/skillsskills/workers-best-practicesandskills/wrangler(Apache-2.0, pin41e0d198).
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.
- 15d ago Changed · +9 lines ca18f6426017
- 1mo ago First seen · 47 lines · 0 tokens per session scan A 56d108854f70
ops-serverless is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 548 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 2026-09-03.
Other commands, from other repositories
deploy
Deploy application with pre/post-deploy checks.
deps-update
Audit and update dependencies safely.
auto-claude
Invoke Auto-Claude autonomous coding framework for complex feature implementation.
update-counts
Explicitly refresh public toolkit and committed marketplace source snapshots and numeric documentation.
cancel-ralph
Cancel active Ralph Wiggum loop.
handoff
Write a session handoff document for continuity.