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/watermelonbros/reado/claude-mdgit clone --depth 1 https://github.com/WatermelonBros/readoWrote 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/watermelonbros/reado/claude-md)<a href="https://agentmods.dev/instructions/watermelonbros/reado/claude-md"><img src="https://agentmods.dev/badge/instructions/watermelonbros/reado/claude-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 | $0.00951 | $0.00951 |
| Opus 5 | $0.00476 | $0.00476 |
| Sonnet 5 | $0.00190 | $0.00190 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
reado 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 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.
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reado — working notes
UI components
Build on Ark UI, not from scratch. @ark-ui/react is a
dependency; use its headless primitives for any interactive base component
(dialogs, menus, tooltips, segmented controls, selects, checkboxes, QR codes, …)
and style them with our Tailwind tokens. Don't hand-roll focus traps, keyboard
nav, positioning, or ARIA that Ark already provides. Import per component, e.g.
import { Tooltip } from "@ark-ui/react/tooltip".
Reach for the shared atoms before writing raw markup. Common UI is a
component, not a copy-pasted <button className="…">:
Button(atoms/Button.tsx) — text buttons (primary/secondary/ghost/danger, sizessm/md). Never restyle a bare<button>for a text action.IconButton(atoms/IconButton.tsx) — every clickable icon.labelis required (it is botharia-labeland the tooltip); passactivefor toggles,dangerfor destructive actions. It carries an Ark-basedTooltip, so a migrated icon button needs notitle.Tooltip(atoms/Tooltip.tsx) — Ark tooltip;IconButtonuses it.GlobalTooltip(the legacytitle-scraping singleton) is the interim fallback for buttons not yet onIconButton; preferIconButton/Tooltipfor new code and migrate old buttons toward them.
If a component isn't trivial and Ark has it, use Ark. If clickable UI repeats, promote it to an atom rather than duplicating classes.
Phosphor icons
The atoms/icons.tsx set wraps Phosphor. Import the *Icon-suffixed exports
(CaretRightIcon, not the deprecated bare CaretRight).
Code style
Biome owns formatting and lint (biome.jsonc): no
semicolons, double quotes, 100 columns, imports organized. pnpm lint is the
read-only check CI runs; pnpm lint:fix applies everything it flags. Don't
hand-format — run the fixer.
CI fails on a single diagnostic and the check is required on main, so a rule
left enabled is a rule the code obeys. The handful that are off carry their
reason inline in biome.jsonc; turning one back on means fixing its sites, not
suppressing them one by one.
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.
- today Changed · +19 lines · +270 tokens per session 4235a6b552d3
- 4d ago First seen · 55 lines · 681 tokens per session scan A d3edb5e7d4a0
reado CLAUDE.md is an instructions file published in the GitHub repository WatermelonBros/reado (22 stars, last pushed today), licensed MIT. It adds 951 tokens to every session, about $0.0048 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
crystal CLAUDE.md
Instructions for stravu/crystal, covering crystal - multi-session claude code manager, project overview, references, implementation status: ✅ complete and ✅ implemented features.
easy-cheese python.instructions.md
Instructions for paulnsorensen/easy-cheese, covering hard rules, what to flag and what not to flag.
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core, parameterized queries, migration strategy.
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.
AmbyKit CLAUDE.md
Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.