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/hoangyell/markdy-com/copilot-instructionsgit clone --depth 1 https://github.com/HoangYell/markdy-comWrote 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/hoangyell/markdy-com/copilot-instructions)<a href="https://agentmods.dev/instructions/hoangyell/markdy-com/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/hoangyell/markdy-com/copilot-instructions.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 | $0.00426 | $0.00426 |
| Opus 5 | $0.00213 | $0.00213 |
| Sonnet 5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
markdy-com copilot-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.
What it actually says
Copilot instructions for this repository
- When the user says
ship it,release it, or gives shorthand likecommit, PR, merge, release, tag it, interpret that as a request to run the full shipping workflow for the current completed changes. - The default shipping workflow for this repo is:
- validate the current change with the full CI suite:
pnpm run ci(runs unit tests, AST backward compatibility gates, documentation examples, and Chrome DevTools headless E2E verification) - commit the finished product changes with a repo-style commit message
- open a PR and wait for checks
- merge the PR once checks pass
- cut the next patch release with
pnpm run release <next-version> - ensure
CHANGELOG.mdcontains concrete release notes before the release commit is created - push the version tag and confirm the GitHub Release workflow succeeds
- validate the current change with the full CI suite:
- Prefer the existing release automation in scripts/release.sh instead of manually stitching together a release flow.
- All 8 packages are dual-published:
- npmjs.com: Distributed under
@markdy/*(e.g.@markdy/core,@markdy/renderer-dom,@markdy/mcp-server) - GitHub Packages: Distributed under
@hoangyell/*onhttps://npm.pkg.github.comviascripts/publish-packages.mjs
- npmjs.com: Distributed under
- CI runs 4 parallelized jobs (
quality,testmatrix across Node 20 & 22,devtools-e2e, andwebsite). Thequalityjob runspnpm run buildprior topnpm run typecheckto ensure emitted declarations are available for cross-package workspace imports. - Keep the homepage example picker curated. Favor the strongest showcase scenes and avoid cluttering the homepage with weak, repetitive, or overly diagnostic examples.
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 · 18 lines · 426 tokens per session scan A fd9842f0afbd
markdy-com copilot-instructions.md is an instructions file published in the GitHub repository HoangYell/markdy-com (88 stars, last pushed today), licensed MIT. It adds 426 tokens to every session, about $0.0021 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
emdash AGENTS.md
AGENTS.md instructions for emdash-cms/emdash, covering rules, workflow, architecture, code patterns and database: never interpolate into sql.
u-he-preset-randomizer AGENTS.md
Instructions for Fannon/u-he-preset-randomizer, covering agents.md, project overview, architecture, core modules and development workflow.
openrouter-genimage-kote-claude-code AGENTS.md
AGENTS.md instructions for koteyye/openrouter-genimage-kote-claude-code, a project described as: Generate and edit images through OpenRouter directly from Claude Code.
glyphloop CLAUDE.md
Claude Code instructions for ideoshi/glyphloop, covering glyphloop, commands, generating animations as an agent, architecture and conventions.
after-effects-mcp CLAUDE.md
Instructions for Engine-Room-Games/after-effects-mcp, covering claude development guide — after-effects-mcp, what this project is, how the pieces talk, source layout and the op pipeline (in detail).
animation-principles CLAUDE.md
Claude Code instructions for dylantarre/animation-principles, covering claude code integration, what this repository contains, skill location, how to use skills and finding the right skill.