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/aker-dev/microfolio/claude-mdgit clone --depth 1 https://github.com/aker-dev/microfolioWhat 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 | $0.06000 | $0.06000 |
| Opus 5 | $0.03000 | $0.03000 |
| Sonnet 5 | $0.01200 | $0.01200 |
| Haiku 4.5 | $0.00600 | $0.00600 |
Grade A, and why
microfolio CLAUDE.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 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
.mcp.json declares the official Svelte MCP server (@sveltejs/mcp): live documentation and a svelte-autofixer that validates Svelte source. Prefer it over recalling Svelte 5 semantics from memory. It replaced svelte-complete.txt, an 810 KB documentation dump that had been frozen since July 2025.
.claude/settings.json allowlists this project's own scripts so pnpm lint, pnpm build and friends run without a prompt.
Project Overview
microfolio is a static portfolio generator built with SvelteKit 2, Svelte 5, and Tailwind CSS 4. It uses a file-based CMS (Markdown + YAML frontmatter) for content. Developed by AKER.
The 1.0 stability promise (README › Stability) freezes until 2.0: the content layout and frontmatter keys, the keys of config.js (add-only), the commands, and the files update-microfolio never touches. A change to any of those is a major version, not a minor.
Development Commands
pnpm dev # Development server (port 5555)
pnpm build # Production build (via build.js → vite build)
pnpm deploy # Build with NODE_ENV=production (sets /microfolio base path)
pnpm preview # Preview production build (port 2001)
pnpm lint # Prettier check + ESLint
pnpm format # Prettier auto-fix
pnpm optimize-images # Generate WebP thumbnails via sharp
pnpm clean-images # Remove generated optimized images
pnpm test # Unit tests (Vitest, single run)
pnpm test:watch # Unit tests in watch mode
pnpm test:e2e # End-to-end tests (Playwright, against pnpm dev)
pnpm test:smoke # Smoke tests (Playwright, against build/ — run pnpm deploy first)
pnpm screenshots # Regenerate doc/screenshots (needs a dev server; PORT=…)
Those two ports are a Daft Punk nod — Interstella 5555, and Discovery, the album it sets to pictures. strictPort is deliberately unset, so a busy port sends Vite to the next one and it prints where it actually landed. playwright.config.js and scripts/screenshots.js both default to 5555 because each means "wherever the dev server is": Playwright reuses a running one rather than starting its own, and the screenshot script requires one.
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 · 177 lines · 6,000 tokens per session scan A ee80b100facf
microfolio CLAUDE.md is an instructions file published in the GitHub repository aker-dev/microfolio (141 stars, last pushed 6d ago), licensed MIT. It adds 6,000 tokens to every session, about $0.0300 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
viperadnan-git.github.io CLAUDE.md
Claude Code instructions for viperadnan-git/viperadnan-git.github.io, covering portfolio project - claude context, project overview, tech stack, project structure and data loading system.
al-folio AGENTS.md
Instructions for alshedivat/al-folio, covering agent guidelines for al-folio (v1.x), route your change, stop sign, three failures that produce no error message and validated local command set.
al-folio CLAUDE.md
Instructions for alshedivat/al-folio, covering claude.md, daily dev loop, optional toolchains, docker serving model (v1-specific) and ci gates and the style contract.
al-folio copilot-instructions.md
Instructions for alshedivat/al-folio, covering copilot coding agent instructions (v1.x), where to look, copilot-specific paths and ci expectations.
al-folio javascript-scripts.instructions.md
Instructions for alshedivat/al-folio, covering javascript instructions (v1.x), ownership, guidance and validation.
al-folio liquid-templates.instructions.md
Instructions for alshedivat/al-folio, covering liquid templates instructions (v1.x), ownership, guidance and validation.