mirador: Instructions file for Claude Code

CLAUDE.md

mirador CLAUDE.md is an instructions file for Claude Code from jchultarsky/mirador. It costs 31,262 tokens per session, scanned B, original, MIT.

A Claude Code instruction file describing Mirador, a Rust terminal dashboard for clock, weather, tasks, and live system metrics. It records project context, design reasoning, commands, and architecture for people or agents joining the repository.

In plain words
What is it for?
Use it as working context when developing, reviewing, or handing off the Mirador repository.
Why use it?
It prevents developers from having to reconstruct the project's purpose and conventions from the code alone.

Instructions file for Claude Code

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

This is jchultarsky/mirador's own configuration. It tells Claude Code how to work on mirador 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 mirador configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/julian/.zshrc:.:127:.

Reuse

Borrowing it

Nothing to install: this file belongs to jchultarsky/mirador. 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/jchultarsky/mirador/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jchultarsky/mirador

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 mirador CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jchultarsky/mirador/claude-md"><img src="https://agentmods.dev/badge/instructions/jchultarsky/mirador/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31,262 This file is loaded in full into every session.
When invoked 31,262 The same file — it is already loaded in full.
Security scan B 2 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 $0.31262 $0.31262
Opus 5 $0.15631 $0.15631
Sonnet 5 $0.06252 $0.06252
Haiku 4.5 $0.03126 $0.03126

Measured today against content hash e88507800db6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

mirador CLAUDE.md scanned grade B with 2 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 today.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

A rename installs a new file, created per the umask, so `chmod 600` on a task

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`curl -sL .../api/v1/crates/mirador/<version>/readme`, and **`-L` is
CLAUDE.md · 2,124 lines

How it starts

The opening of the file, as written. The whole thing — 2,124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — working notes for mirador

Context for anyone (human or agent) picking this repo up cold. Design rationale that belongs to users lives in README.md and CONTRIBUTING.md; this file is the stuff you would otherwise have to reverse-engineer from the diff.

There was a HANDOFF.md alongside this carrying the perishable half — where work stopped, what was waiting on a decision. Its open items are all either done or folded in below, so it has been deleted as it asked to be. Write another the same way if you hand off mid-flight, and delete it the same way.

What this is

A personal information dashboard for the terminal, in Rust + ratatui. Clock, weather, tasks, and live system metrics in a config-driven grid. MIT licensed. Repo: github.com/jchultarsky/mirador. Owner: Julian Chultarsky.

A mirador is a lookout — the tower you climb to see everything at once.

Known name collision, accepted knowingly: Project Mirador, the IIIF image viewer. Raised before the name was chosen; not a reason to revisit it.

The one-line pitch that shapes every decision

A tab you leave open all day and come back to. That constrains more than it sounds like it does: no ambient blinking, no shimmering graphs, no doomscroll hooks, calm by default so that not calm is legible at a glance.

Commands

cargo test                                    # all fast, no network, no fixtures
cargo clippy --all-targets -- -D warnings     # must be silent
cargo fmt --all -- --check                    # must be silent
RUSTDOCFLAGS="-D warnings" \
  cargo doc --no-deps --document-private-items  # CI runs this; it caught a
                                                # broken intra-doc link that
                                                # the other three did not
cargo run -- --print-config > /tmp/m.toml     # scratch config to experiment on
cargo run -- --config /tmp/m.toml

The bar is zero warnings and zero errors across all four. Running only the first three is how a red build reached main: rustdoc rejects a link to a cfg(test) item, and nothing else notices.

Read the full file on GitHub · 2,124 lines

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. today Changed · +169 lines · +2,788 tokens per session e88507800db6
  2. 6d ago Changed · +84 lines · +1,262 tokens per session ec38418ba5de
  3. 10d ago First seen · 1,871 lines · 27,212 tokens per session scan B 4c68a8f246d5

Subscribe to this mod's changes

mirador CLAUDE.md is an instructions file published in the GitHub repository jchultarsky/mirador (299 stars, last pushed today), licensed MIT. It adds 31,262 tokens to every session, about $0.1563 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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 · 6,785 tokens

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.

github/spec-kit · 7,104 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens