Borrowing it
Nothing to install: this file belongs to beel-collab/presets.dev. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/beel-collab/presets.dev/main/release/terraform/native/copilot/.github/instructions/terraform.instructions.mdgit clone --depth 1 https://github.com/beel-collab/presets.devWrote 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/instructions/beel-collab/presets.dev/terraform)<a href="https://agentmods.dev/instructions/beel-collab/presets.dev/terraform"><img src="https://agentmods.dev/badge/instructions/beel-collab/presets.dev/terraform/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/instructions/beel-collab/presets.dev/terraform"><img src="https://agentmods.dev/badge/instructions/beel-collab/presets.dev/terraform.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 | $0.00689 | $0.00689 |
| Opus 5.5 | $0.00276 | $0.00276 |
| Sonnet 5.5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
presets.dev terraform.instructions.md 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 today.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terraform Copilot Instructions: Providers, State and Plan Review
Path-specific Copilot instructions for Terraform. They apply through applyTo and leave .github/copilot-instructions.md in place.
Updated for Terraform 1.17, Nov 2026
Do not upgrade dependencies or the framework version unless the task asks.
Stay on the Terraform version in .terraform-version or the CI image. Terraform 1.17 is the current line to write for when CI is already on it. Do not invent a provider argument. Read the locked provider schema. Required version constraints and the lock file are committed. Do not bump a provider because a plan failed on an unknown attribute you guessed.
Project shape
Modules have a small interface: variables, outputs, and resources. A root module wires providers and backends. A child module does not configure a backend. Names describe the resource, not main copied ten times.
State lives in the remote backend the project already uses, with locking. Do not commit terraform.tfstate. A local state file in a PR is a leak.
Changes
plan is the review artifact. apply and destroy are human actions. Do not run them from an agent turn. A -target apply is a last resort with a written reason.
Read the plan JSON or the plan output for replaces, destroys, and IAM changes. A force_new that replaces a database is a high-severity review, not a routine edit.
Security
IAM actions are the verbs the resource needs. Some AWS actions have no resource-level permission and the resource element must be "*". That star is not, by itself, a finding. A finding is a permission wider than the action requires: extra actions, a star on an action that does support resource ARNs, or 0.0.0.0/0 on an admin port.
Secrets are not in .tfvars committed to git and not in outputs. Mark sensitive outputs. A variable default that contains a key is a bug. Use the project's secret manager or a write-only input.
Provider aliases and regions match the environment. Do not point a dev workspace at a prod account to "see if it plans".
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.
- today First seen · 66 lines · 689 tokens per session scan A a7bd7600c847
presets.dev terraform.instructions.md is an instructions file published in the GitHub repository beel-collab/presets.dev (3 stars, last pushed yesterday), licensed MIT. It adds 689 tokens to every session, about $0.0028 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 2026-11-13.
presets.dev terraform.instructions.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| presets.dev terraform.instructions.mdbeel-collab/presets.dev | Instructions file | 3 | yesterday | MIT | A | 689 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 280k | 2d ago | MIT | A | 4,325 | Codex, OpenCode |