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 skills/microsoft/copilot-camp/dev-camp-documentnpx skills add microsoft/copilot-camp --skill dev-camp-documentgit clone --depth 1 https://github.com/microsoft/copilot-campWhat 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 | $0.00099 | $0.01719 |
| Opus 5 | $0.00049 | $0.00860 |
| Sonnet 5 | $0.00020 | $0.00344 |
| Haiku 4.5 | $0.00010 | $0.00172 |
Grade A, and why
dev-camp-document 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 2d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Camp Word Document Skill
What This Skill Does
Creates a professional Word document on any Copilot Dev Camp lab or Microsoft technology topic by:
- Topic Confirmation — Clarifies the specific lab/topic, audience, and document type
- Research — Performs multiple searches across Microsoft Learn documentation
- Structure — Organizes findings into a logical document outline
- Content Creation — Generates a polished Word document with:
- Professional header and title page
- Table of contents (auto-generated)
- Organized sections with clear hierarchy
- Code examples and architecture diagrams
- Summary tables and comparisons
- Conclusion and next steps
- Formatted citations and references
- Consistent styling throughout
When to Use This Skill
Activate this skill when you need:
- One-pager summary of a Dev Camp lab
- Technical guide or implementation documentation
- Architecture decision record (ADR) for a technology
- Training material or learning guide
- Best practices documentation
- Quick reference guide
- Comparison or evaluation document
- Requirements or design document
Workflow
Step 1: Topic, Audience & Format Selection
Ask the user:
- Topic: Which Dev Camp lab or Microsoft technology? (e.g., "Building AI Agents with Copilot")
- Document Type: What kind of document? (e.g., "One-pager", "Technical Guide", "How-To", "Overview")
- Audience: Who is this for? (e.g., "Developers", "Architects", "Decision Makers", "Operations")
- Length: How detailed? (e.g., "1 page", "3-5 pages", "Comprehensive guide")
Step 2: Multi-Source Research
Conduct multiple searches to gather comprehensive content:
- Search: "[Topic] overview and getting started"
- Search: "[Topic] architecture and design patterns"
- Search: "[Topic] implementation guide and best practices"
- Search: "[Topic] code examples and quickstarts"
- Search: "[Topic] troubleshooting and common issues"
- Search: "[Topic] vs [similar technology]" (if relevant)
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.
- 2d ago First seen · 265 lines · 99 tokens per session scan A 1eb83eec7c2c
dev-camp-document is a skill published in the GitHub repository microsoft/copilot-camp (654 stars, last pushed 18d ago), licensed MIT. It adds 99 tokens to every session and 1,719 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…