Borrowing it
Nothing to install: this file belongs to moztw/www.moztw.org. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/moztw/www.moztw.org/gh-pages/AGENTS.mdgit clone --depth 1 https://github.com/moztw/www.moztw.orgWrote 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/moztw/www.moztw.org/agents-md)<a href="https://agentmods.dev/instructions/moztw/www.moztw.org/agents-md"><img src="https://agentmods.dev/badge/instructions/moztw/www.moztw.org/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 5.1 | $0.00356 | $0.00356 |
| Opus 5 | $0.00178 | $0.00178 |
| Sonnet 5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
www.moztw.org 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 8d 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
Agent Collaboration Notes
When multiple agents are working in parallel, do not let them share the same working directory.
- Use one
git worktreeper agent (each in a separate directory). - Create/use one branch per agent, and keep branch names unique (for example:
codex/<agent-id>/<task>). - Do not run
git checkoutconcurrently in the same worktree. - Merge changes through a single integrator flow (
rebaseorcherry-pick) after each agent provides commit SHA(s).
Build And Source-Of-Truth Rules
This repo uses .shtml as source templates and generates .html files via Grunt.
- Edit source files first:
- Prefer updating
.shtmland include files underinc/. - Do not manually hand-edit generated
.htmlfiles unless the task explicitly requires it.
- Prefer updating
- Build command:
- Before running
npm run build, always wait for manual confirmation from the user that source changes (such as.shtmlorinc/*) are reviewed and approved. - Run
npm run build(same asgrunt build) only after that confirmation, then commit generated files ascommit build results. grunt buildrunscopy(*.shtml->*.html) andssi(flatten includes).
- Before running
- Local preview:
- Run
npm startto start BrowserSync for local checking.
- Run
- News update rule:
- For normal news content updates, update
inc/news.htmlas source. - Let build pipeline regenerate pages such as
index.htmlandnews/index.html; do not maintain those duplicates by hand.
- For normal news content updates, update
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.
- 8d ago First seen · 26 lines · 356 tokens per session scan A 45db39d828f6
www.moztw.org AGENTS.md is an instructions file published in the GitHub repository moztw/www.moztw.org (59 stars, last pushed 6d ago), licensed MPL-2.0. It adds 356 tokens to every session, about $0.0018 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
vscode buildNext.instructions.md
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).
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).
langchain AGENTS.md
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.
spec-kit AGENTS.md
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.