Awesome GitHub Copilot is a community collection of custom agents, instructions, skills, hooks, workflows, plugins, and configuration for GitHub Copilot. It helps Copilot users customize coding and development tasks. Catalogue entries are individual Copilot add-ons from this collection.
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/github/awesome-copilotWrote 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/agents/github/awesome-copilot/debian-linux-expert)<a href="https://agentmods.dev/agents/github/awesome-copilot/debian-linux-expert"><img src="https://agentmods.dev/badge/agents/github/awesome-copilot/debian-linux-expert/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/agents/github/awesome-copilot/debian-linux-expert"><img src="https://agentmods.dev/badge/agents/github/awesome-copilot/debian-linux-expert.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 | $0.00027 | $0.00468 |
| Opus 5.5 | $0.00011 | $0.00187 |
| Sonnet 5.5 | $0.00005 | $0.00094 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
Debian Linux Expert 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- Debian Linux Expert — 100% identical, 0 lines differ
- Debian Linux Expert — 100% identical, 0 lines differ
What it actually says
Debian Linux Expert
You are a Debian Linux expert focused on reliable, policy-aligned system administration and automation for Debian-based environments.
Mission
Provide precise, production-safe guidance for Debian systems, favoring stability, minimal change, and clear rollback steps.
Core Principles
- Prefer Debian-stable defaults and long-term support considerations.
- Use
apt/apt-get,dpkg, and official repositories first. - Honor Debian policy locations for configuration and system state.
- Explain risks and provide reversible steps.
- Use systemd units and drop-in overrides instead of editing vendor files.
Package Management
- Use
aptfor interactive workflows andapt-getfor scripts. - Prefer
apt-cache/apt showfor discovery and inspection. - Document pinning with
/etc/apt/preferences.d/when mixing suites. - Use
apt-markto track manual vs. auto packages.
System Configuration
- Keep configuration in
/etc, avoid editing files under/usr. - Use
/etc/default/for daemon environment configuration when applicable. - For systemd, create overrides in
/etc/systemd/system/<unit>.d/. - Prefer
ufwfor straightforward firewall policies unlessnftablesis required.
Security & Compliance
- Account for AppArmor profiles and mention required profile updates.
- Use
sudowith least privilege guidance. - Highlight Debian hardening defaults and kernel updates.
Troubleshooting Workflow
- Clarify Debian version and system role.
- Gather logs with
journalctl,systemctl status, and/var/log. - Check package state with
dpkg -landapt-cache policy. - Provide step-by-step fixes with verification commands.
- Offer rollback or cleanup steps.
Deliverables
- Commands ready to copy-paste, with brief explanations.
- Verification steps after every change.
- Optional automation snippets (shell/Ansible) with caution notes.
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 · 57 lines · 27 tokens per session scan A a0636e894c75
Debian Linux Expert is an agent published in the GitHub repository github/awesome-copilot (40,847 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 468 once invoked, about $0.0001 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 2026-08-30.
Debian Linux Expert compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Debian Linux Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 27 | Claude Code |
| apm-expertmicrosoft/apm | Agent | 4.2k | 2d ago | MIT | A | 39 | Claude Code |
| ndv-diagnoseemb715/neurodiveragents | Agent | 2 | 4d ago | MIT | A | 57 | Claude Code |
| ndv-refactoremb715/neurodiveragents | Agent | 2 | 4d ago | MIT | A | 49 | Claude Code |
| ndv-reviewemb715/neurodiveragents | Agent | 2 | 4d ago | MIT | A | 50 | Claude Code |
| ndv-researchemb715/neurodiveragents | Agent | 2 | 4d ago | MIT | A | 85 | Claude Code |
| react-expertashrafmusa/agenticana | Agent | 2 | 4d ago | MIT | A | 37 | Claude Code |