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/sherpa-sh/Sherpa-ActionWrote 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/sherpa-sh/sherpa-action/plan-deploy)<a href="https://agentmods.dev/commands/sherpa-sh/sherpa-action/plan-deploy"><img src="https://agentmods.dev/badge/commands/sherpa-sh/sherpa-action/plan-deploy/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/sherpa-sh/sherpa-action/plan-deploy"><img src="https://agentmods.dev/badge/commands/sherpa-sh/sherpa-action/plan-deploy.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 | $0.00007 | $0.00311 |
| Opus 5 | $0.00003 | $0.00156 |
| Sonnet 5 | $0.00001 | $0.00062 |
| Haiku 4.5 | $0.00001 | $0.00031 |
Grade A, and why
plan-deploy 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 8d 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.
What it actually says
Create a deployment plan that consists of infrastructure definitions and what parts of the build project code will get deployed where, and the method for doing it.
- Ask the user what provider they want to deploy to. Ensure we can access the mcp server for that provider. (We currently support cloudflare and AWS native to this Sherpa plugin). If you don't have access tell the user how to fix it, then end the chat and don't continue.
- Use your
manage-infrastructureskill, the.sherpa.sh/build-info.md, and if they exist.sherpa.sh/deployment-plan.md,.sherpa.sh/infrastructure.md, and the latest.sherpa.sh/executionlogto decide what infrastructure needs to be created/updated.Examine the infrastructure and deployment commands in the executionlog. Decide if you should just repeat them. Usually, you want to repeat them. - Make a plan of what you are going to create/update and what code and assets you will deploy and where they will go. Use the skills you have for the framework and for the cloud provider. Think very hard on this step.
- Save this to the file
.sherpa.sh/deployment-plan.md. Use Semantic Versioning at the top of the file, update it if the file already exists. - Think hard and check the plan for any mistakes. Common mistakes are logic, provider, and framework specific issues. If you see mistakes, correct them.
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.
- 8d ago First seen · 11 lines · 7 tokens per session scan A 0e2e27154ca8
plan-deploy is a command published in the GitHub repository sherpa-sh/Sherpa-Action (22 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 311 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
review_pr
Review as a Principal AWS Solutions Architect. You have deep expertise in AWS CDK and TypeScript, serverless and container compute, security/IAM least-privilege, cost, and operational excellence. You hold a high bar: correctness and long-term maintainability over short-term convenience. You are direct, specific, and…
scan
Scan AWS account for cost optimization.
oma:modernize
A command that starts a six-stage process for updating an existing legacy workload on AWS. It coordinates workload assessment, strategy selection, target architecture, container packaging, and production cutover, with risk checks and an audit trail between stages.
oma-platform-bootstrap
A command-based process for deploying an agentic AI platform on Amazon EKS, a managed Kubernetes service. It follows five checkpoints from gathering context through validation.
aws-kb
Read-only AWS knowledge lookup — query docs, CLI reference, SOPs, comparisons, onboarding pointers, and next-step recommendations from the kb MCP server. Stateless per turn; never writes spec artefacts.
checklist
Generate a custom checklist for the current feature based on user requirements.