Borrowing it
Nothing to install: this file belongs to konstruktoid/hardened-images. 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/konstruktoid/hardened-images/master/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/konstruktoid/hardened-imagesWrote 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/konstruktoid/hardened-images/copilot-instructions)<a href="https://agentmods.dev/instructions/konstruktoid/hardened-images/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/konstruktoid/hardened-images/copilot-instructions/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/konstruktoid/hardened-images/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/konstruktoid/hardened-images/copilot-instructions.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 | $0.01138 | $0.01138 |
| Opus 5 | $0.00569 | $0.00569 |
| Sonnet 5 | $0.00228 | $0.00228 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
hardened-images copilot-instructions.md scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- curl-pipe-to-shell patterns in build/provisioning scripts. How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Instructions for GitHub Copilot
This repository builds hardened Ubuntu server images (Azure VM image, QEMU
.qcow2, and formerly .ova) using Packer and the
konstruktoid/ansible-collection-hardening
Ansible collection. Prefer secure-by-default, operationally reliable,
maintainable, and auditable changes.
Mission and baseline
- Preserve existing hardening intent unless an explicit deviation is requested.
- Bias recommendations toward CIS Benchmarks, DISA STIG guidance, and CMMC-oriented practices.
- Prefer minimal, reviewable, reversible diffs.
- The build must remain reproducible without external dependencies beyond the official Ubuntu ISO, Packer, QEMU/OVMF, and the pinned hardening collection version — do not introduce hidden network fetches or unpinned tooling.
Engineering expectations
- Packer templates (
*.pkr.hcl) should stay declarative; keep provisioning logic inscripts/orconfig/local.ymlrather than inline in HCL. - Shell scripts (
build_box.sh,azure_vars_export,scripts/*.sh) must passshellcheck(enforced via.pre-commit-config.yaml) and useset -euo pipefail(or equivalent explicit error handling). - Favor maintainability over clever one-liners.
- Ansible usage in
config/local.ymlshould stay module-first and use FQCN (ansible.builtin.*) — see.github/instructions/ansible.instructions.md.
Security requirements
- Never hardcode secrets, credentials, keys, tokens, or passwords. Azure
credentials (
ARM_*) must never be persisted to disk or committed. - Treat SSH access, the
ubuntuaccount/password, sudo, PAM, audit/logging, firewall (ufw), mounts, sysctl, services, and authentication settings as high-sensitivity areas — these are set by thekonstruktoid.hardeningrolesconfig/local.ymlselects and by the vars it passes them. - The ephemeral Packer provisioning SSH keypair must always be stripped by
scripts/cleanup.shbefore a build finishes; do not weaken or bypass that cleanup step. - Avoid security relaxations (e.g.
sshd_password_authentication, dropping a role fromconfig/local.yml, disabling audit rules) unless explicitly requested and documented with rationale.
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.
- 5d ago Changed · +13 tokens per session 2fa0be0cf0ba
- 10d ago First seen · 101 lines · 1,125 tokens per session scan A a7795d5817c1
hardened-images copilot-instructions.md is an instructions file published in the GitHub repository konstruktoid/hardened-images (90 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,138 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.