DuckCoding CLAUDE.md

A set of Claude Code instructions for contributing to the DuckCoding project, including its development rules, commands, workflow, and quality checks.

In plain words
What is it for?
Use it when developing in the DuckCoding repository and when you need its commands, documentation-reading requirements, or zero-warning quality standards.
Why use it?
It helps an agent follow the project's expected process instead of guessing how changes should be made or checked.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/duckcoding-dev/duckcoding/claude-md
Clone the repo
git clone --depth 1 https://github.com/DuckCoding-dev/DuckCoding
Per session 10,677 This file is loaded in full into every session.
When invoked 10,677 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
Origin unknown 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 $0.10677 $0.10677
Opus 5 $0.05339 $0.05339
Sonnet 5 $0.02135 $0.02135
Haiku 4.5 $0.01068 $0.01068

Measured 2d ago against content hash e5a86ef17694, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

DuckCoding CLAUDE.md scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Codex 使用需要设置 ~/.codex/config.toml 中的
CLAUDE.md · 411 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 2d ago First seen · 411 lines · 10,677 tokens per session scan B e5a86ef17694

Subscribe to this mod's changes

DuckCoding CLAUDE.md is an instructions file published in the GitHub repository DuckCoding-dev/DuckCoding (140 stars, last pushed 6mo ago), licensed AGPL-3.0. It adds 10,677 tokens to every session, about $0.0534 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.