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/mldangelo/personal-site/agents-mdgit clone --depth 1 https://github.com/mldangelo/personal-siteWrote 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/mldangelo/personal-site/agents-md)<a href="https://agentmods.dev/instructions/mldangelo/personal-site/agents-md"><img src="https://agentmods.dev/badge/instructions/mldangelo/personal-site/agents-md.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 | $0.03656 | $0.03656 |
| Opus 5 | $0.01828 | $0.01828 |
| Sonnet 5 | $0.00731 | $0.00731 |
| Haiku 4.5 | $0.00366 | $0.00366 |
Grade A, and why
personal-site AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working on this Next.js personal portfolio site.
Quick Commands
npm run dev # Start dev server (localhost:3000)
npm run format # Format with Prettier + Biome (run before committing)
npm run lint # Biome linting
npm run type-check # TypeScript checking
npm test # Vitest tests
npm run build # Production build + static export
File-scoped (faster feedback):
npx biome check path/to/file.tsx # Lint single file
npm test -- ComponentName # Test single component
Project Structure
app/ → Pages, layouts, global CSS
app/styles/ → Modular CSS (tokens, base, components, layout, pages)
src/components/ → React components (organized by feature)
src/data/ → Static data (resume, projects, contact)
src/hooks/ → Custom React hooks
content/writing/ → Blog posts (Markdown with frontmatter)
src/data/writing.ts → External writing links shown on `/writing`
public/images/ → Images and favicons
docs/ → Documentation
Code Style
Do:
- Use TypeScript strict mode, functional components with hooks
- Style with CSS custom properties in
app/styles/(tokens intokens/, components incomponents/) - Keep components small and focused
- Use existing patterns from similar components
- Mark client components with
'use client' - Follow conventional commits:
feat:,fix:,chore:,docs: - Run
npm run formatbefore committing (CI enforces this)
Don't:
- Add new dependencies without clear need
- Create god components or monolithic files
- Hard-code colors—use CSS variables (
var(--color-*)) - Skip type annotations on function parameters
- Commit without running
npm run formatfirst
Git Workflow
- Create a topic branch for every task; never commit or push directly to
main - Make small, frequent conventional commits as you go (e.g.,
feat:,fix:,refactor:) - Push to your remote branch after every commit to keep it in sync
- Land changes on
mainby merging GitHub PRs with conventional-commit titles (deploys trigger automatically from these merges) - If multiple PRs need to land together, open an integration branch PR; do not locally merge into
main - Treat
mainas protected: force-pushes and history rewrites require explicit user approval
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 · 128 lines · 3,656 tokens per session scan A 01a37e976c9d
personal-site AGENTS.md is an instructions file published in the GitHub repository mldangelo/personal-site (1,683 stars, last pushed 15d ago), licensed MIT. It adds 3,656 tokens to every session, about $0.0183 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
gitprofile AGENTS.md
AGENTS.md instructions for arifszn/gitprofile, covering agents.md, what this project is, customizing a portfolio: edit one file, the base option is the most common source of breakage and layout.
terminal AGENTS.md
Instructions for m4tt72/terminal, covering agents.md - repository guide for agentic coding, project overview, commands, development and testing.
devportfolio CLAUDE.md
Instructions for RyanFitzgerald/devportfolio, covering claude.md, project overview, tech stack, development commands and architecture.
karngyan.com CLAUDE.md
Instructions for karngyan/karngyan.com, covering claude.md, commands, architecture, conventions and recipes.
gitprofile CLAUDE.md
Claude Code instructions for arifszn/gitprofile, a project described as: 🚀 Create and publish a GitHub-synced portfolio by just providing your GitHub username.
NextWeb4.github.io AGENTS.md
AGENTS.md instructions for NextWeb4/NextWeb4.github.io, covering agents.md, 1. project structure, 2. run commands, 3. test commands and 4. build commands.