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/saeloun/miru-web/agents-mdgit clone --depth 1 https://github.com/saeloun/miru-webWrote 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/saeloun/miru-web/agents-md)<a href="https://agentmods.dev/instructions/saeloun/miru-web/agents-md"><img src="https://agentmods.dev/badge/instructions/saeloun/miru-web/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 | $0.01163 | $0.01163 |
| Opus 5 | $0.00581 | $0.00581 |
| Sonnet 5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
miru-web 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 5d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is the source of truth for AI assistant behavior in this repository. If guidance conflicts elsewhere, prefer this file.
Scope: entire repository.
Keep this file short. Treat it as a router for repo-specific rules.
Core Repo Rules
- Never fake results. Do not claim something works unless you actually verified it.
- For UI changes, verify in a real browser on the running app.
- For JavaScript or TypeScript changes, always run
rtk mise exec -- timeout 30 bin/vite buildbefore handoff. - For runtime-sensitive commands in this repo, prefer
rtk mise exec -- <command>. Ifrtkblocks the task, fall back and say so plainly. - Use
apply_patchfor manual file edits. - Run focused specs for files you change before widening scope.
- For browser-facing fixes, verify on the local app with Playwright or PinchTab.
- Do not claim a React or JS crash is fixed unless the affected page loads successfully in the browser and is checked for console errors.
- If a change is verified and there is no explicit reason to hold it back, commit and push it when asked instead of letting the tree drift.
- Preserve unrelated work in a dirty tree. Do not revert user changes just to simplify your own task.
- When the user asks for a larger batch, keep going until the batch is done, blocked, or risky without input.
- When resolving GitHub issues and posting resolution comments (with user approval), include verification images/screenshots as evidence.
- Before merging any PR, inspect CodeRabbit review feedback and fix every actionable item. Do not merge with unresolved CodeRabbit feedback unless the user explicitly approves deferring a specific item.
- For GitHub issue fixes, always create or use a dedicated git worktree before editing files; do not make issue fixes directly in the primary checkout.
Repo Workflow
- When a user gives a sequence like "finish A, then do B", complete A and continue into B without waiting.
- On SPA pages, prefer settled route checks over generic
networkidlewhen background requests stay alive. - If a user reports a live production bug, reproduce it on the real domain when practical before declaring root cause.
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.
- 5d ago First seen · 70 lines · 1,163 tokens per session scan A 7967d6319076
miru-web AGENTS.md is an instructions file published in the GitHub repository saeloun/miru-web (266 stars, last pushed 14d ago), licensed MIT. It adds 1,163 tokens to every session, about $0.0058 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
five_things AGENTS.md
AGENTS.md instructions for emmvs/five_things, covering coding standards, security, rubocop, dry and i18n / translations.
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
orm AGENTS.md
AGENTS.md instructions for prisma/orm, covering agents — prisma next, start here, modular onboarding, project overview and where skills and rules live.
qiankun AGENTS.md
Instructions for umijs/qiankun, covering qiankun project knowledge base, structure, architecture (big picture), commands and build (vite 8 → package javascript; tsc → declarations).
joint CLAUDE.md
Claude Code instructions for clientIO/joint, covering claude.md, project overview, common commands, install dependencies and build distribution files (runs grunt).
qiankun CLAUDE.md
Instructions for umijs/qiankun: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.