microsoft/copilot-camp is a collection of hands-on workshops for extending Microsoft 365 Copilot and building custom engine agents. Developers use it to learn how to create declarative agents, connectors, MCP servers, multi-agent workflows, API integrations, and other Copilot extensions. The catalogue entries are skills and instructions for these development workflows.
Borrowing it
Nothing to install: this file belongs to microsoft/copilot-camp. 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/microsoft/copilot-camp/main/.github/skills/copilot-dev-camp-lab-author/SKILL.mdgit clone --depth 1 https://github.com/microsoft/copilot-campWrote 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/microsoft/copilot-camp/copilot-dev-camp-lab-author)<a href="https://agentmods.dev/skills/microsoft/copilot-camp/copilot-dev-camp-lab-author"><img src="https://agentmods.dev/badge/skills/microsoft/copilot-camp/copilot-dev-camp-lab-author/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/microsoft/copilot-camp/copilot-dev-camp-lab-author"><img src="https://agentmods.dev/badge/skills/microsoft/copilot-camp/copilot-dev-camp-lab-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 122 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00062 | $0.01732 |
| Opus 5.5 | $0.00025 | $0.00693 |
| Sonnet 5.5 | $0.00012 | $0.00346 |
| Haiku 4.5 | $0.00006 | $0.00173 |
Grade A, and why
copilot-dev-camp-lab-author 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.
How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Dev Camp Lab Author
Purpose
Author a new lab file for Copilot Dev Camp, with the right structure and writing style, and place it in the correct docs path.
Required Inputs
Collect all required values before creating the lab:
- Target subfolder under
docs/pages. - Lab number.
- Lab unique code.
- Lab title.
- Knowledge-base URLs (web sites/pages to use for grounded content).
- Badge suggestions (
badgeId,badgeName) forcc-award.
If the target subfolder is missing, ask for it. If the lab number is missing, ask for it. If knowledge-base URLs are missing, ask for them before drafting content.
File Placement Rules
- Create the file only under
docs/pages/<subfolder>/. - Use markdown file extension
.md. - Suggested naming pattern:
<lab-number>-<slug>.md. - If file already exists, ask whether to pick a new number/slug or update existing content.
Frontmatter Requirements
Every lab markdown file must begin with YAML frontmatter containing the following fields:
---
code: <lab-unique-code>
title: <lab-title>
description: <brief-description-of-lab>
tags: [tag1, tag2, tag3]
level: <100|200|300|400|500>
time: <time-to-complete-in-minutes>
badge: <badge-code>
products: [product1, product2]
created-date: <YYYY-MM-DD>
last-edited-date: <YYYY-MM-DD>
---
Frontmatter Field Definitions
- code: Unique identifier for the lab (e.g.,
WIQ01). - title: Lab title matching the lab title in content.
- description: 1-2 sentence summary of what students will learn (infer the value from the lab content, once created).
- tags: Comma-separated list (ask user) converted to YAML list. Examples:
agents,copilot,m365. - level: Difficulty level:
100(beginner),200(intermediate),300(advanced),400(expert),500(professional). - time: Estimated time in minutes to complete the lab (infer the value based on the length of the content, once created).
- badge: The badge code issued upon lab completion (e.g.,
WorkIQ-Expert). - products: Comma-separated list (ask user) converted to YAML list. Examples:
Teams,Copilot,SharePoint,Work IQ. - created-date: Lab creation date in
YYYY-MM-DDformat. - last-edited-date: Most recent edit date in
YYYY-MM-DDformat.
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 · 217 lines · 62 tokens per session scan A 1b4c0e5987a6
copilot-dev-camp-lab-author is a skill published in the GitHub repository microsoft/copilot-camp (676 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 1,732 once invoked, about $0.0002 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.
copilot-dev-camp-lab-author compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| copilot-dev-camp-lab-authormicrosoft/copilot-camp | Skill | 676 | 2d ago | MIT | A | 62 | Claude Code, Codex |
| hr-onboardingnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 32k | today | MIT | A | 138 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 73 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 81 | Claude Code |
| eli5companion-inc/feynman | Skill | 10k | 6d ago | MIT | A | 63 | Claude Code, Codex |
| deck-course-modulenexu-io/html-anything | Skill | 9.4k | 24d ago | Apache-2.0 | A | 25 | Claude Code, Codex |