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 agentmods add instructions/thesethrose/copilot-skills/create-skillgit clone --depth 1 https://github.com/TheSethRose/Copilot-SkillsWrote 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/thesethrose/copilot-skills/create-skill)<a href="https://agentmods.dev/instructions/thesethrose/copilot-skills/create-skill"><img src="https://agentmods.dev/badge/instructions/thesethrose/copilot-skills/create-skill.svg" alt="Measured on agentmods" 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 | $0.02214 | $0.02214 |
| Opus 5 | $0.01107 | $0.01107 |
| Sonnet 5 | $0.00443 | $0.00443 |
| Haiku 4.5 | $0.00221 | $0.00221 |
Grade A, and why
Copilot-Skills create-skill.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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Skill - Instructions
When working with skill creation files or when queries contain skill-related keywords, use this context.
Constitutional Principles (Required for All Skills)
1. Progressive Disclosure
Information organized in layers: metadata → core workflow → optional details
Checklist:
- ✓ YAML frontmatter with: description, model (optional), tools (optional)
- ✓ Core workflow scannable in <3 minutes
- ✓ Detail files are optional, not required to use skill
- ✓ Each layer independent and self-contained
Anti-pattern: Requiring users to read all documentation before using skill
2. File-Based Organization
Skills are organized as files in specific locations, not in databases or external systems.
Structure:
.github/
├── prompts/{skill-name}.prompt.md # Always required
├── instructions/{skill-name}.instructions.md # Always required
└── copilot-skills/{skill-name}/ # Optional
├── README.md
├── scripts/ # Optional
├── patterns.md # Optional
└── reference.md # Optional
Required Paths:
- Prompt:
.github/prompts/{skill-name}.prompt.md - Instructions:
.github/instructions/{skill-name}.instructions.md
Anti-pattern: Storing skill definitions in external APIs or databases
3. Dynamic Discovery
Skills are discoverable by AI agents via keywords and file patterns.
Implementation:
- Keywords defined in prompt file YAML
- Entry in
.github/copilot-instructions.md(keyword routing map) - File patterns in instructions file
description:field - Clear use cases in prompt
Example routing map entry:
#### Skill Name
**Keywords**: keyword1, keyword2, keyword3
**Suggest**: `/skill-name`
**Auto-context**: `.github/instructions/skill-name.instructions.md`
**Skill**: `.github/copilot-skills/skill-name/README.md`
Anti-pattern: Skills that can't be found without manual documentation
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.
- 4d ago First seen · 314 lines · 2,214 tokens per session scan A 3f7be7dd3210
Copilot-Skills create-skill.instructions.md is an instructions file published in the GitHub repository TheSethRose/Copilot-Skills (3 stars, last pushed 8mo ago), licensed MIT. It adds 2,214 tokens to every session, about $0.0111 per session on Opus 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.
Other instructions, from other repositories
copilot copilot-instructions.md
Copilot instructions for navikt/copilot, covering copilot instructions for navikt/copilot, repository overview, nav development standards, nav principles and nav tech stack.
copilot AGENTS.md
AGENTS.md instructions for navikt/copilot, covering agents.md for navikt/copilot, what this repo is, efficiency rule, standard commands and conventions.
Project Guidelines
VS Code extension project guidelines for GitHub Copilot Insights. Covers project shape, code style, VS Code extension rules, build and test, and repository discipline.
Repo Validation Workflow
Use when: changing, validating, testing, or reviewing this VS Code extension repository. Covers npm compile, lint, test harness, Electron test caveats, and build output.
sensei AGENTS.md
Instructions for spboyer/sensei, covering agents.md, repository structure, key conventions, skill.md format and skill body (markdown).
SonarCloud-Skill-Agent-Guidance
Repository guidance for the SonarCloud/SonarQube findings management skill.