What is flog CLAUDE.md?

Repository instructions for Claude Code working on the Rust project flog. They explain the project structure, design boundaries, build and test commands, and which documentation to read before making changes.

Use them when modifying flog, especially for locating modules, understanding its data protocol, following contribution and coding rules, and running the right checks.

They reduce the risk of changing the wrong part of the code or breaking rules that keep the user interface separate from the rest of the application.

How shaominngqing/flog configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to shaominngqing/flog. 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/shaominngqing/flog/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/shaominngqing/flog

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/shaominngqing/flog/claude-md/github.svg)](https://agentmods.dev/instructions/shaominngqing/flog/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/shaominngqing/flog/claude-md"><img src="https://agentmods.dev/badge/instructions/shaominngqing/flog/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/shaominngqing/flog/claude-md"><img src="https://agentmods.dev/badge/instructions/shaominngqing/flog/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,998 This file is loaded in full into every session.

When invoked 4,998 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 91% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.04998	$0.04998
Opus 5.5	$0.01999	$0.01999
Sonnet 5.5	$0.01000	$0.01000
Haiku 4.5	$0.00500	$0.00500

Measured 2mo ago against content hash 70702887c4e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

flog 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 2mo 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.

Origin

This is a copy

91% identical to flog AGENTS.md — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Before non-trivial changes, read docs/ARCHITECTURE.md first, then docs/MODULES.md to locate the right file, and docs/PROTOCOL.md for wire-format detail. Process rules live in docs/CONTRIBUTING.md; code-style rules in docs/CODING_STYLE.md; UI framework boundaries in docs/UI_FRAMEWORK_BOUNDARY.md.

🛡️ Design rules that outlive the codebase

These rules guard against regressions that would make future work (including a planned GUI frontend) expensive. They apply to every commit, human or AI:

UI layer only reads App, never writes business state. Renderers may only write LayoutCache. Business mutations belong to event/apply.rs or App methods.
domain/ parser/ input/ transport/ app/ must NEVER use ratatui / use crossterm / any UI framework. This is the UI-agnostic core; it must stay portable to a future GUI. event/ may depend on exactly one input framework (currently crossterm), but must translate framework signals to neutral ClickRegion / (future) KeyAction enums before they reach App mutations.
Input events must go through the two-phase detect/apply pattern. detect_click_region(&App, x, y) -> Option<ClickRegion> is pure and testable. apply_click_region(&mut App, region, class) performs mutations. Never interleave the two. See Phase 3 Step 3.6.
New state must be derivable by pure functions without assuming a TUI cell grid. If your state requires a Frame or Rect to make sense, it belongs in ui/ or LayoutCache (R5 of UI_FRAMEWORK_BOUNDARY.md), not in App.
File size budget is a signal, not a law. Under 500 lines is default. 500-800 yellow (document the reason). Over 800 red (must split). Test files (*_tests.rs sibling pattern) are exempt. Per CONTRIBUTING.md §5.5.
Every B-class bug gets a red-locked characterization test. #[ignore = "bug: <audit-id>"] test lands first; un-ignore in the same commit as the fix. No shadow TODOs, no silent fixes.

Read the full file on GitHub · 183 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.

2mo ago First seen · 183 lines · 4,998 tokens per session scan A 70702887c4e5

Subscribe to this mod's changes

flog CLAUDE.md is an instructions file published in the GitHub repository shaominngqing/flog (4 stars, last pushed 3mo ago), licensed MIT. It adds 4,998 tokens to every session, about $0.0200 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to flog AGENTS.md, differing in 10 lines, and is treated as a copy.

adb android dart devtools dio

flog CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
flog CLAUDE.mdshaominngqing/flog	Instructions file	4	3mo ago	MIT	A	4,998	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

flog: Instructions file for Claude Code