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 skills add trsdn/github-copilot-agent --skill copilot-customization-selectorgit clone --depth 1 https://github.com/trsdn/github-copilot-agentWrote 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/trsdn/github-copilot-agent/copilot-customization-selector)<a href="https://agentmods.dev/skills/trsdn/github-copilot-agent/copilot-customization-selector"><img src="https://agentmods.dev/badge/skills/trsdn/github-copilot-agent/copilot-customization-selector/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/skills/trsdn/github-copilot-agent/copilot-customization-selector"><img src="https://agentmods.dev/badge/skills/trsdn/github-copilot-agent/copilot-customization-selector.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 | $0.00067 | $0.04091 |
| Opus 5.5 | $0.00027 | $0.01636 |
| Sonnet 5.5 | $0.00013 | $0.00818 |
| Haiku 4.5 | $0.00007 | $0.00409 |
Grade C, and why
copilot-customization-selector scanned grade C 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Block `rm -rf` and `DROP TABLE` commands How it starts
The opening of the file, as written. The whole thing — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customization Selector
This skill helps you decide which GitHub Copilot customization option to use for your specific needs.
When to use this skill
- User asks "what type of customization should I create?"
- User wants to understand differences between instructions, prompts, agents, and skills
- User needs to choose the right approach for a new customization
- User asks "should I use a prompt or an instruction file?"
Quick Decision Flowchart
What do you want to achieve?
│
├─► Define coding standards/rules that apply automatically?
│ └─► Use CUSTOM INSTRUCTIONS (.instructions.md)
│
├─► Create a reusable task template (e.g., "generate tests")?
│ └─► Use PROMPT FILES (.prompt.md)
│
├─► Create a specialized AI persona with specific tools?
│ └─► Use CUSTOM AGENTS (.agent.md)
│
├─► Build portable capabilities with scripts/resources?
│ └─► Use AGENT SKILLS (SKILL.md)
│
├─► Automate actions at agent lifecycle points?
│ └─► Use HOOKS (.github/hooks/*.json)
│
├─► Connect external services or APIs?
│ └─► Use MCP SERVERS (mcp.json)
│
└─► Install pre-packaged customizations?
└─► Use AGENT PLUGINS (preview)
Decision Matrix
| Feature | Instructions | Prompt Files | Custom Agents | Agent Skills | Hooks | MCP | Plugins | Tool Sets |
|---|---|---|---|---|---|---|---|---|
| File Extension | .instructions.md |
.prompt.md |
.agent.md |
SKILL.md |
.json |
.json / YAML frontmatter |
plugin.json |
.jsonc |
| Location | .github/instructions/ |
.github/prompts/ |
.github/agents/ |
.github/skills/<name>/ |
.github/hooks/ |
.vscode/mcp.json, agent mcp-servers, plugin .mcp.json |
plugin root | tool-set file via VS Code |
| Triggers | Auto (always or via glob) | Manual (/name) |
Manual (switch agent) | Auto (when relevant) | Lifecycle events | Tool/resource/prompt invocation | Install/enable plugin | Tool selection or #toolset |
| Can include scripts? | No | No | No | Yes | Yes | Server-dependent | Yes | No |
| Can specify tools? | No | Yes | Yes | No | N/A | Provides tools | Bundles tools via agents/MCP | Groups tools |
| Can specify model? | No | Yes | Yes | No | N/A | No | Via bundled prompts/agents | No |
| Portable across tools? | VS Code/GitHub | VS Code | Partial | Open standard | Partial | MCP standard | Cross-tool (preview) | VS Code |
| Status | Stable | Stable | Stable (1.106+) | Stable | Preview | Stable/Preview features | Preview | Stable/Preview |
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.
- 1mo ago First seen · 417 lines · 67 tokens per session scan C e99272a38569
copilot-customization-selector is a skill published in the GitHub repository trsdn/github-copilot-agent (3 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 4,091 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
code-review-csharp
Perform structured code reviews of C# source code covering naming conventions, performance, security, readability, and .NET best practices. Trigger phrases include "review this C# code", "check my C# for best practices", "analyze this C# class", "find issues in my C# code".
self-awareness-review
Reviews a given week of your OWN Teams meetings, chats, and sent emails to surface moments where you may have misread social signals or come across as passive-aggressive, curt, sarcastic, or dismissive — returning the exact quote, how it likely landed, and a kinder rewrite. Private self-reflection coaching for the…
commit
Create well-formatted Git commits with conventional commit messages. Use this skill when the user wants to create a commit.
semantic-model-disambiguation
Analyze Power BI semantic models for column-level overlaps that confuse Copilot and Fabric data agents. Detect ambiguity, review with domain expert, apply fixes via MCP.
prompt-2-data
Generate comprehensive synthetic relational data for any specified subject with multiple normalized CSV files maintaining referential integrity.
audit
Audits recent work against its Definition of Done and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. Generates an incremental prompt pack for any gaps found. With…