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 agentmods add skills/srnichols/plan-forge/infra-deploynpx skills add srnichols/plan-forge --skill infra-deploygit clone --depth 1 https://github.com/srnichols/plan-forgeWrote 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/srnichols/plan-forge/infra-deploy)<a href="https://agentmods.dev/skills/srnichols/plan-forge/infra-deploy"><img src="https://agentmods.dev/badge/skills/srnichols/plan-forge/infra-deploy.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.01085 |
| Opus 5 | $0.00019 | $0.00543 |
| Sonnet 5 | $0.00008 | $0.00217 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
infra-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 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Infrastructure Deploy Skill
Trigger
"Deploy infrastructure" / "Deploy to staging" / "Run azd up" / "Apply Terraform"
Steps
1. Pre-Flight Checks
# Verify active subscription and context
az account show --query "{name: name, id: id}"
# Confirm the target environment
Write-Host "Deploying to: $env:AZURE_ENV_NAME"
# For Bicep: lint before anything
az bicep lint --file infra/main.bicep
# For Terraform
terraform init
terraform fmt -check -recursive
terraform validate
2. What-If / Plan
# Bicep — what-if
az deployment group what-if \
--resource-group $resourceGroup \
--template-file infra/main.bicep \
--parameters infra/main.parameters.json
# Terraform
terraform plan -out=tfplan
# azd
azd provision --preview
3. Deploy
# Bicep
az deployment group create \
--resource-group $resourceGroup \
--template-file infra/main.bicep \
--parameters infra/main.parameters.json \
--name "deploy-$(Get-Date -Format 'yyyyMMdd-HHmm')"
# Terraform
terraform apply tfplan
# azd (full lifecycle)
azd up --no-prompt
4. Verify
# Check deployment status
az deployment group list \
--resource-group $resourceGroup \
--query "[?properties.provisioningState=='Succeeded'] | [-1].name"
# Integration / smoke tests
Invoke-Pester -Path ./tests/integration -Output Detailed
# List any non-succeeded resources
az resource list \
--resource-group $resourceGroup \
--query "[?properties.provisioningState!='Succeeded'].{Name:name, Type:type, State:properties.provisioningState}"
Safety Rules
- ALWAYS run what-if / plan before applying
- ALWAYS confirm the subscription before deploying to production
- NEVER apply to production without a preceding staging deployment
- NEVER auto-approve destructive changes (resource replacement or deletion)
- Ask before applying any plan that shows resource deletion
Rollback
# Bicep — list recent deployments, redeploy N-1
az deployment group list \
--resource-group $resourceGroup \
--query "sort_by([?properties.provisioningState=='Succeeded'], &properties.timestamp)[-2].name" \
--output tsv
# Terraform
git revert HEAD
terraform apply
# azd
azd down --force # deprovision, then re-up from last commit
git revert HEAD && azd up
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 First seen · 136 lines · 39 tokens per session scan A 66e41b606f5c
infra-deploy is a skill published in the GitHub repository srnichols/plan-forge (5 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 1,085 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 skills, from other repositories
orchestrator
Use this skill when running as an ephemeral orchestrator subagent for a Taniwha project. The skill instructs the agent to read project state from disk, decide the single next action the dispatcher should take, write that decision back to disk, and exit. Trigger this whenever the dispatcher has invoked an orchestrator…
dispatcher
Use this skill when running a Taniwha build from the main Claude Code session. The skill turns the main session into a thin, mechanical executor that follows instructions from ephemeral orchestrator subagents. Trigger this whenever the user wants to start a Taniwha build, resume an interrupted one, or work on a…
contract-derivation
Use this skill after a design document exists and before any module is implemented. It takes a design doc and derives per-module contracts (manifests) that are complete enough for an implementor working in isolation to build each module correctly without seeing the rest of the system. Trigger this whenever the user…
verifier
Use this skill when verifying that a completed Taniwha implementation or composition satisfies its contract's acceptance criteria. The verifier reads the contract, the implementation's source files, and the project context, then writes its own tests against the contract's acceptance criteria, runs them, and reports…
go
Project Kickstart - PRD-First Orchestrator.
docs
Use this agent when you need to create comprehensive technical and user documentation for approved features, tests, or debugged issues.