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/pwd9000-ml/github-copilot-bootcamp/currriculum-stylinggit clone --depth 1 https://github.com/Pwd9000-ML/GitHub-Copilot-BootcampWrote 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/pwd9000-ml/github-copilot-bootcamp/currriculum-styling)<a href="https://agentmods.dev/instructions/pwd9000-ml/github-copilot-bootcamp/currriculum-styling"><img src="https://agentmods.dev/badge/instructions/pwd9000-ml/github-copilot-bootcamp/currriculum-styling.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 | $0.00450 | $0.00450 |
| Opus 5 | $0.00225 | $0.00225 |
| Sonnet 5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
Currriculum-Styling 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 5d 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.
What it actually says
Language and spelling
- Use British English spelling throughout all curriculum files. Common substitutions: "customise" not "customize", "behaviour" not "behavior", "organisation" not "organization", "optimise" not "optimize", "recognise" not "recognize", "analyse" not "analyze".
Formatting and structure
- Use consistent heading hierarchy across all markdown files: one H1 per page for the page title, H2 for major sections, H3 for subsections.
- Use consistent formatting for lists and links across all markdown files.
- Do not use em dashes (—). Use a full stop (.) or a comma (,) to separate clauses instead.
- When listing prerequisites, use bullet points and keep each item concise.
Code blocks
- In every code block, include a comment that explains the purpose of the code and any important detail that learners should be aware of.
Page completeness
- Every page must end with a
## Next Stepssection that links to the next page in the curriculum or to additional resources. Exception: FAQ documents do not require a Next Steps section.
Issue templates
- Issue templates must include clear, specific sections for the user to fill out (for example: "What did you try?", "What happened?", "Expected behaviour", "Actual behaviour").
- When curriculum content changes, review the corresponding issue template and update it if the changed content is referenced.
README maintenance
- When curriculum content or structure changes, update the root
README.mdto reflect those changes. - After any update, set the
**Last Updated:** DD/MM/YYYYline near the top ofREADME.mdto today's date in DD/MM/YYYY format.
Adding a new week
- When adding a brand new week of content, use the
weekly-curriculumskill in.github/skills/weekly-curriculum/SKILL.md. It enforces the folder layout, file naming, placeholder fill-in, styling rules, and README updates automatically.
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.
- 5d ago First seen · 37 lines · 450 tokens per session scan A 4e0f46d6fd27
Currriculum-Styling is an instructions file published in the GitHub repository Pwd9000-ML/GitHub-Copilot-Bootcamp (23 stars, last pushed 3mo ago), licensed MIT. It adds 450 tokens to every session, about $0.0022 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 instructions, from other repositories
ab100 CLAUDE.md
Instructions for timothywarner-org/ab100, covering claude.md, repository purpose, slide deck build, source decks (microsoft ab-100t00) and course structure (4 hours).
ab100 copilot-instructions.md
Instructions for timothywarner-org/ab100, covering copilot instructions, repository purpose, key locations, skill and agent conventions and mcp server ids.
Alex_Skill_Mall critical-thinking.instructions.md
Critical thinking framework — challenge assumptions, evaluate evidence, detect bias, and test falsifiability.
atelier copilot-instructions.md
Instructions for ahamedzoha/atelier, covering github copilot instructions, before you help, the mode controls how much code you write and always.
training_hub CLAUDE.md
Claude Code instructions for Red-Hat-AI-Innovation-Team/training_hub, a project described as: An algorithm-focused interface for common llm training, continual learning, and reinforcement learning techniques.
ai-lesson-planner copilot-instructions.md
Copilot instructions for saniales/ai-lesson-planner, covering project guidelines, code style, architecture, build and test and project conventions.