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/htetaunglin-coder/htetaunglin-coder.dev/agents-mdgit clone --depth 1 https://github.com/htetaunglin-coder/htetaunglin-coder.devWhat 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 | $0.02468 | $0.02468 |
| Opus 5 | $0.01234 | $0.01234 |
| Sonnet 5 | $0.00494 | $0.00494 |
| Haiku 4.5 | $0.00247 | $0.00247 |
Grade A, and why
htetaunglin-coder.dev 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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- htetaunglin-coder.dev CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Portfolio Agent Guide
Cross-tool agent guide for htetaunglin-coder.dev. AGENTS.md and CLAUDE.md are identical — edit one, mirror the other in the same commit.
Keep this file short. Deep docs live in agent_docs/; load one only when the task touches it. The code wins over this file — if they disagree, say so instead of silently picking one.
This is NOT the Next.js you know
This repo runs Next.js 16, which breaks things your training data predates. Before changing routing, layouts, metadata, images, fonts, CSS, caching, route handlers, server actions, or next.config.mjs, verify the current API — don't recall it. Heed deprecation notices in build output rather than silencing them.
Check, in order: the installed package's own types under node_modules/next/ and the patterns already in src/app, then the Vercel plugin's nextjs skill (next-upgrade for version bumps), then https://nextjs.org/docs. This version ships no docs at node_modules/next/dist/docs/ — don't go looking for that path.
Already caught here: params and searchParams page props are promises — await them.
Project
Personal portfolio and writing site for Htet Aung Lin. Live and public on Vercel, deployed from main, no staging.
Next.js 16 (App Router, Turbopack dev) · React 19 · TypeScript strict · Tailwind v4 · Motion · Fumadocs MDX · AI SDK v6 + Groq · Resend · Upstash/Vercel KV · Cloudinary · Giscus · Biome + Ultracite · pnpm, Node 24.
Alias: @/* → src/*. Route map, boundaries, and env vars: agent_docs/project-map.md.
Commands
pnpm dev · build · start · preview · types:check (tsc --noEmit) · check (Ultracite) · fix (Ultracite autofix) · resume:pdf (regenerates the committed resume PDF via headless Chrome — only when asked).
There is no test runner. No Vitest, no Playwright, no pnpm test. Don't invent one and never claim tests pass. Verification here is types:check + check + build + actually looking at the page.
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.
- 3d ago First seen · 118 lines · 2,468 tokens per session scan A 988e53b53258
htetaunglin-coder.dev AGENTS.md is an instructions file published in the GitHub repository htetaunglin-coder/htetaunglin-coder.dev (5 stars, last pushed 3d ago), licensed MIT. It adds 2,468 tokens to every session, about $0.0123 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 2026-08-31.
Other instructions, from other repositories
data-table-filters CLAUDE.md
Instructions for openstatusHQ/data-table-filters, covering claude.md, project overview, monorepo structure (pnpm + turborepo), key commands and database.
www-sacred AGENTS.md
Instructions for internet-development/www-sacred, covering agents.md, what this repo is, repo map, conventions and the fonts menu previews.
karakeep CLAUDE.md
Claude Code instructions for karakeep-app/karakeep, a project described as: A self-hostable bookmark-everything app (links, notes and images) with AI-based automatic tagging and full text search.
Codex-Skills AGENTS.md
Instructions for TheGoat395/Codex-Skills, covering repository operating notes, required checks, evidence rules and change hygiene.
souls-directory CLAUDE.md
Instructions for thedaviddias/souls-directory, covering claude.md — project context for ai assistants, project overview, tech stack, critical rules and database is convex.
agentgram CLAUDE.md
Instructions for agentgram/agentgram, covering claude.md — agentgram development guide, project overview, tech stack, monorepo structure and core architecture patterns.