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/ikcode-dev/copilot-kit/ai-content-xml-tagsgit clone --depth 1 https://github.com/ikcode-dev/copilot-kitWhat 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 | $0.01961 | $0.01961 |
| Opus 5 | $0.00981 | $0.00981 |
| Sonnet 5 | $0.00392 | $0.00392 |
| Haiku 4.5 | $0.00196 | $0.00196 |
Grade A, and why
XML-like Tags for AI Content 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XML-like Tags for AI-Consumed Content
Markdown files in .github/agents/, .github/skills/, .github/prompts/, and .github/instructions/ are consumed primarily by AI agents, not humans. Standard Markdown conveys structure (headers, lists, tables) but not content type — the agent can't reliably distinguish "follow this instruction" from "output this template" from "learn from this example."
XML-like tags solve this by wrapping content blocks with explicit semantic boundaries. They tell the agent what kind of content a block is and how to process it.
When to Use Tags
Use XML-like tags when Markdown alone creates ambiguity about content type. Specifically:
- Templates vs instructions — Is a code block something to fill in and output, or an example to learn from? Wrap it in
<template>or<example>. - Hard rules vs advisory guidance — Are these bullet points non-negotiable constraints or suggestions? Wrap them in
<rules>or<best-practices>. - Agent content vs user content — Should the agent process this internally or display it verbatim? Wrap user-facing output in
<user-message>. - Action items vs reference material — Should the agent iterate through a checklist or read it for context? Wrap checklists in
<validation>or<questions>.
Do not use tags when Markdown is unambiguous on its own — explanatory prose, section introductions, and standard tables don't need wrapping.
Tag Vocabulary
Every tag below is part of the standard vocabulary. Use these exact tag names — do not invent one-off tags.
Action Tags (agent should DO something with this content)
| Tag | Purpose | Agent action |
|---|---|---|
<questions> |
Interview questions to ask the user before proceeding | Iterate through and ask each question |
<validation> |
Checklist to verify before reporting completion | Iterate through every item and confirm |
<context-gathering> |
Steps for scanning workspace/environment before acting | Execute each scan step in order |
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 · 207 lines · 1,961 tokens per session scan A e59710b6ca2f
XML-like Tags for AI Content is an instructions file published in the GitHub repository ikcode-dev/copilot-kit (29 stars, last pushed 5mo ago), licensed MIT. It adds 1,961 tokens to every session, about $0.0098 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.