agentmods.dev

Mira: Instructions file for Claude Code

CLAUDE.md

Mira CLAUDE.md is an instructions file for Claude Code from byteseek/Mira. It costs 490 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Mira, a market-research workspace and assistant. They point to the files that define its identity, operating rules, research workflow, and startup guidance.

In plain words
What is it for?
Use them when starting Mira, handling a market-research request, updating Mira, or answering questions about how the workspace works.
Why use it?
They keep Mira’s behavior consistent and make clear which instructions to read for onboarding, research tasks, updates, and memory-related requests.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

This is byteseek/Mira's own configuration. It tells Claude Code how to work on Mira itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Mira configures →

not rated 277repo 1mo ago A scan 490 tokens original Apache-2.0
View source ↗ byteseek/Mira
Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/byteseek/Mira/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/byteseek/Mira

Made for: Claude Code.

Wrote 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.

agentmods badge for Mira CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/byteseek/mira/claude-md/github.svg)](https://agentmods.dev/instructions/byteseek/mira/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/byteseek/mira/claude-md"><img src="https://agentmods.dev/badge/instructions/byteseek/mira/claude-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.

agentmods 80×15 button for Mira CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/byteseek/mira/claude-md"><img src="https://agentmods.dev/badge/instructions/byteseek/mira/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 490 This file is loaded in full into every session.
When invoked 490 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00490 $0.00490
Opus 5.5 $0.00196 $0.00196
Sonnet 5.5 $0.00098 $0.00098
Haiku 4.5 $0.00049 $0.00049

Measured 1mo ago against content hash 2c2f1a13406f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Mira 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 1mo 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.

CLAUDE.md · 37 lines

What it actually says

Mira Instructions For Claude Code

This repository is the Mira market-research workspace.

When working in Claude Code, follow the same project protocol as Codex. Do not duplicate the rules manually; use the root files as the source of truth:

  1. Read AGENTS.md for the operating rules.
  2. Read MIRA.md for the wake word, identity contract, persona boundary, and memory rules.
  3. Read OPERATING_CONTRACT.md for the one-screen lazy-loading contract.
  4. Read START_HERE.md when the user asks how to start, what Mira covers, or wants prompt examples.
  5. Read AGENT_QUICKSTART.md for agent execution details, routing, output locations, and required evidence discipline.
  6. When the user says Mira, enter Mira Mode.

Minimum execution rules:

  • On an empty first prompt, hi Mira, 你好 Mira, Mira mode, or an onboarding request, return a concise START_HERE.md summary before any research workflow.
  • If the first prompt is already a concrete research task, do not block with onboarding; route the task and optionally mention Mira help.
  • For update mira / Mira self-update requests, run scripts/mira_update.sh directly.
  • For Mira help, 怎么用 Mira, Mira 能做什么 or start here, return the layered user-facing entry card from START_HERE.md.
  • For standard / deep_dive research, run scripts/check_updates.sh once (local-first by default, with a 24h remote TTL); quick_map / 看一下 tasks skip it. A blocked fetch degrades to local refs and is reported — never elevate sandbox permissions for a freshness check. Then route the task with loops/analysis-routing.md.
  • Keep facts, inferences, judgments, evidence trails, and refresh conditions explicit.
  • Use position, portfolio, instrument, and trade-action framing only within the gates named in OPERATING_CONTRACT.md.

Mira Mode is a research and documentation protocol, not a promise of background automation.

Changes

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.

  1. 1mo ago First seen · 37 lines · 490 tokens per session scan A 2c2f1a13406f

Subscribe to this mod's changes

Mira CLAUDE.md is an instructions file published in the GitHub repository byteseek/Mira (277 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 490 tokens to every session, about $0.0020 per session on Opus 5.5. 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.

Claude Codeagent-workflowai-agentscodexdecision-logearnings-analysis
Related

Other instructions, from other repositories

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,581 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

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.

deepseek-ai/deepseek-harness · 4,261 tokens