dual-ai-paper-coach: Command for Claude Code

.claude/commands/CLAUDE.md

CLAUDE is a command for Claude Code from dengxu11111/dual-ai-paper-coach. It costs 0 tokens per session (844 once invoked), scanned A, original, MIT.

A set of instructions for Claude Code slash commands stored in `.claude/commands/`. Each command defines the steps, expected output, and restrictions that apply when a user runs it.

In plain words
What is it for?
Defining commands such as drafting, reviewing, iterating, checking claims, and finalizing work in Claude Code.
Why use it?
It keeps command behavior consistent and prevents important rules from being hidden inside individual prompts. It also helps maintain a small, controlled set of project workflows.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is dengxu11111/dual-ai-paper-coach's own configuration. It tells Claude Code how to work on dual-ai-paper-coach 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 dual-ai-paper-coach configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dengxu11111/dual-ai-paper-coach. 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/dengxu11111/dual-ai-paper-coach/main/.claude/commands/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dengxu11111/dual-ai-paper-coach

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 CLAUDE

README.md
[![agentmods](https://agentmods.dev/badge/commands/dengxu11111/dual-ai-paper-coach/claude/github.svg)](https://agentmods.dev/commands/dengxu11111/dual-ai-paper-coach/claude)
Your own site
<a href="https://agentmods.dev/commands/dengxu11111/dual-ai-paper-coach/claude"><img src="https://agentmods.dev/badge/commands/dengxu11111/dual-ai-paper-coach/claude/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 CLAUDE

Your own site · 80×15
<a href="https://agentmods.dev/commands/dengxu11111/dual-ai-paper-coach/claude"><img src="https://agentmods.dev/badge/commands/dengxu11111/dual-ai-paper-coach/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 844 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00844
Opus 5 $0.00000 $0.00422
Sonnet 5 $0.00000 $0.00169
Haiku 4.5 $0.00000 $0.00084

Measured 12d ago against content hash 9dae0a66b133, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

CLAUDE 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 12d 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/commands/CLAUDE.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md (.claude/commands/ subdirectory rules)

This file extends the root CLAUDE.md + prompts/ management rules with extra constraints that apply inside .claude/commands/.

What you're editing

.claude/commands/*.md defines the slash commands that the user runs in Claude Code. Each markdown file describes one command's input / steps / output / red lines.

When the user types /draft, Claude Code injects the entire draft.md content as system instructions for the session — every word in here will be acted on. Treat it more strictly than ordinary documentation.

Five core slash commands (stabilize these before adding more)

Command File
/draft draft.md
/codex-review codex-review.md
/iterate iterate.md
/claim-check claim-check.md
/finalize finalize.md

Before adding a sixth command, confirm that the main workflow genuinely needs it.

Hard constraints when editing a command

Rule 1: reference prompts, never inline them (single exception below)

Wrong: hard-coded system prompt inside the command markdown.

# /draft
Read the following system prompt:

  You are a scientific writing assistant... (30 lines of inlined prompt)

Right: reference prompts/*.md.

# /draft
Read `prompts/writer_system.md` as the system rules.
Read `prompts/draft_paper.md` as the task template.

Single exception: claim-check.md inlines the cross-model scoring prompt — see the Prompt management rule section in the root CLAUDE.md. Every other command strictly follows "reference, don't inline".

Rule 2: cross-process independence (for codex-review / iterate)

When invoking a Codex subprocess:

  • Must include the --skip-git-repo-check flag
  • Must not pass prompts/writer_system.md to Codex (that would poison independent review)
  • Must not let Claude review the paper itself (you only trigger Codex — courier role)

Rule 3: output path locked to my-paper/

Read the full file on GitHub · 89 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. 12d ago First seen · 89 lines · 0 tokens per session scan A 9dae0a66b133

Subscribe to this mod's changes

CLAUDE is a command published in the GitHub repository dengxu11111/dual-ai-paper-coach (12 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 844 tokens. 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.