What is iac-self-service?

A workflow for generating Terraform configuration for Azure infrastructure using an organisation’s approved modules. Terraform is a tool that describes cloud infrastructure in configuration files, and Azure is Microsoft’s cloud platform.

Use it to scaffold compliant Azure resource groups, networks, storage, databases, AKS clusters, and Key Vault resources for a project.

It helps keep new infrastructure within approved modules, naming rules, regions, tags, and security standards. It also validates the generated configuration and surfaces remaining warnings.

iac-self-service — Skill for Claude Code and Codex by net9876

Install

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.

Any agent

npx skills add net9876/claude-iac-mcp-server --skill iac-self-service

Clone the repo

git clone --depth 1 https://github.com/net9876/claude-iac-mcp-server

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/net9876/claude-iac-mcp-server/iac-self-service/github.svg)](https://agentmods.dev/skills/net9876/claude-iac-mcp-server/iac-self-service)

Your own site

<a href="https://agentmods.dev/skills/net9876/claude-iac-mcp-server/iac-self-service"><img src="https://agentmods.dev/badge/skills/net9876/claude-iac-mcp-server/iac-self-service/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/net9876/claude-iac-mcp-server/iac-self-service"><img src="https://agentmods.dev/badge/skills/net9876/claude-iac-mcp-server/iac-self-service.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 992 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00089	$0.00992
Opus 5.5	$0.00036	$0.00397
Sonnet 5.5	$0.00018	$0.00198
Haiku 4.5	$0.00009	$0.00099

Measured 2mo ago against content hash cd3510aa1d48, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

iac-self-service 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 2mo 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.

skills/iac-self-service/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Acme IaC Self-Service

You help developers provision Azure infrastructure that complies with Acme's standards. The acme-iac-platform MCP server is the source of truth for approved modules and standards. Approved modules are Azure Verified Modules (AVM) plus any of Acme's own git-hosted modules registered in the catalog.

Golden rules

Only approved modules. Never write raw resource "azurerm_*" blocks for anything covered by a module. Discover with list_modules / search_modules, read specs with get_module. (Raw resources are acceptable ONLY for things no module covers — and call that out explicitly.)
Standards first. Call list_standards before generating anything. Honor the naming pattern, allowed regions, required tags, and security baseline.
Generate, don't guess. Use generate_module_usage to scaffold blocks — it wires naming, the correct resource-group reference, and mandatory tags. Then fill the returned todo_inputs from the module spec.
Always validate. Run validate_config on the final HCL. Resolve every error before presenting. Surface warnings to the user.
Secrets are never literals. Use the Key Vault module's native secrets / secrets_value inputs, or a write-only argument (e.g. administrator_password_wo) so the value never lands in HCL.

AVM specifics you MUST get right

Resource-group reference differs per module. generate_module_usage handles it, but when wiring by hand: storage, virtual-network, and AKS take parent_id = module.resource_group.resource_id; key-vault and postgres take resource_group_name = module.resource_group.name.
Key Vault manages secrets natively. The AVM key-vault module has secrets + secrets_value inputs and a secrets output — do NOT add raw azurerm_key_vault_secret resources.
Postgres password. Prefer administrator_password_wo (write-only) fed from a random_password, so it never persists in state (SEC-SECRET-001 / SEC-STATE-001).
Key Vault needs tenant_id → data.azurerm_client_config.current.tenant_id (add the data "azurerm_client_config" "current" {} block once).

Read the full file on GitHub · 79 lines

Changes

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.

2mo ago First seen · 79 lines · 89 tokens per session scan A cd3510aa1d48

Subscribe to this mod's changes

iac-self-service is a skill published in the GitHub repository net9876/claude-iac-mcp-server (0 stars, last pushed 5mo ago), licensed MIT. It adds 89 tokens to every session and 992 once invoked, about $0.0004 per session on Opus 5.5. 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.

Cloud DevOps and cloud

iac-self-service next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
iac-self-servicenet9876/claude-iac-mcp-server	Skill	0	5mo ago	MIT	A	89	Claude Code, Codex
gke-compute-classesgoogle/skills	Skill	24k	yesterday	Apache-2.0	A	83	Claude Code, Codex
gke-reliabilitygoogle/skills	Skill	24k	yesterday	Apache-2.0	A	85	Claude Code, Codex
gke-workload-securitygoogle/skills	Skill	24k	yesterday	Apache-2.0	A	171	Claude Code, Codex
cloud-architectJeffallan/claude-skills	Skill	12k	8d ago	MIT	A	71	Claude Code
nemo-automodel-launcher-configNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	30	Claude Code
azure-mgmt-botservice-dotnetmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	78	Claude Code