Borrowing it
Nothing to install: this file belongs to byteseek/Mira. 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/byteseek/Mira/main/AGENTS.mdgit clone --depth 1 https://github.com/byteseek/MiraWrote 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/byteseek/mira/agents-md)<a href="https://agentmods.dev/instructions/byteseek/mira/agents-md"><img src="https://agentmods.dev/badge/instructions/byteseek/mira/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/byteseek/mira/agents-md"><img src="https://agentmods.dev/badge/instructions/byteseek/mira/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01393 | $0.01393 |
| Opus 5 | $0.00696 | $0.00696 |
| Sonnet 5 | $0.00279 | $0.00279 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade A, and why
Mira 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mira Agent Guide
This repository is the Mira research workspace. Mira is a named research
protocol, not a fictional personality, adviser, trade bot, or background
automation promise.
Read Order
MIRA.mdfor the wake word, identity boundary, and memory contract.OPERATING_CONTRACT.mdfor the one-screen lazy-loading map.START_HERE.mdwhen the user asks how to start, what Mira covers, or wants prompt examples.AGENT_QUICKSTART.mdonly when agent execution details, output locations, or extended examples are needed.
Fast Paths
| user intent | do this |
|---|---|
empty first prompt, hi Mira, 你好 Mira, Mira mode, or onboarding request |
Return a concise START_HERE.md summary before any research workflow. |
update mira, Mira self-update, 从 GitHub 拉最新 Mira |
Run scripts/mira_update.sh. Do not run scripts/check_updates.sh first. |
Mira help, 怎么用 Mira, Mira 能做什么, start here |
Return the layered Start Here card from START_HERE.md; keep it user-facing and concise. |
start a standard / deep_dive research task |
Run scripts/check_updates.sh once (local-first by default, 24h remote TTL; add --always-fetch to force a remote check now). Report if behind; never auto-update or elevate sandbox permissions — a blocked fetch degrades to cached local refs and is disclosed. |
start a quick_map / 看一下 task |
Skip the freshness check; it is not worth a network round-trip for throwaway triage. |
Mira, 看一下 X |
Treat as quick_map; route first, then answer with source notes and refresh triggers. |
time-sensitive market question (今天, 现在, 目前, latest, intraday, premarket, after-hours, crash/pullback) |
Run data/time-policy.md Market-Date Resolution, then data/live-data-source-policy.md; anchor relative dates to the market timezone, search or refresh live sources before judging, and show quote/publish time plus freshness caveat. |
现在能不能买/卖 X, 能不能加/减/追/抄底 X, actionability ask |
Run data/marginal-buyer-payoff-bridge.md before data/actionability-risk-control.md; identify marginal buyer/seller, payoff source, repricing trigger, priced-in status and failure mode before posture. |
| daily/weekly market report, market brief, 盘前简报, 收盘复盘, 日报, 周报 | Use loops/market-briefing-loop.md; set market_scope, briefing_type, quote/publish time, source notes and escalation queue. |
Mira, 研究 X |
Use loops/research-loop.md unless routing selects a narrower path. |
Mira, 更新 X |
Use loops/monitoring-loop.md; focus on incremental evidence and thesis impact. |
| earnings, guidance, or transcript work | Use skills/earnings-report-analysis/ before updating a standard research package. |
| research report, sell-side note, rating change, target price, or user-provided report/PDF | Use skills/research-report-interpretation/; run ingestion/restricted-source handling before using the report as evidence. |
| methodology reliability | Use loops/methodology-research-loop.md. |
| PM, position, portfolio, or decision review | Use the matching review loop from OPERATING_CONTRACT.md. |
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.
- 9d ago First seen · 80 lines · 1,393 tokens per session scan A 5e7de00f26bb
Mira AGENTS.md is an instructions file published in the GitHub repository byteseek/Mira (267 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,393 tokens to every session, about $0.0070 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.