What is respond-to-referee?

A writing aid for turning journal referee comments into a response letter and matching LaTeX changes. It can handle one comment or create a complete reply document.

Use it to answer a specific point from a referee report or prepare a full response document from a Markdown or text report.

It removes the need to organize responses and edits manually while keeping the reply clear and appropriately worded.

How Alexander-M-Dickerson/ai-asset-pricing configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Alexander-M-Dickerson/ai-asset-pricing. 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/Alexander-M-Dickerson/ai-asset-pricing/main/.claude/skills/respond-to-referee/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Alexander-M-Dickerson/ai-asset-pricing

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/skills/alexander-m-dickerson/ai-asset-pricing/respond-to-referee/github.svg)](https://agentmods.dev/skills/alexander-m-dickerson/ai-asset-pricing/respond-to-referee)

Your own site

<a href="https://agentmods.dev/skills/alexander-m-dickerson/ai-asset-pricing/respond-to-referee"><img src="https://agentmods.dev/badge/skills/alexander-m-dickerson/ai-asset-pricing/respond-to-referee/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/skills/alexander-m-dickerson/ai-asset-pricing/respond-to-referee"><img src="https://agentmods.dev/badge/skills/alexander-m-dickerson/ai-asset-pricing/respond-to-referee.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,728 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.

Model	Per session	Once invoked
Fable 5.1	$0.00024	$0.01728
Opus 5.5	$0.00010	$0.00691
Sonnet 5.5	$0.00005	$0.00346
Haiku 4.5	$0.00002	$0.00173

Measured 2mo ago against content hash 918de47e0bc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

respond-to-referee 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.

.claude/skills/respond-to-referee/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Respond to Referee Skill

Structured workflow for addressing referee comments. Operates in two modes:

Single-point mode: Draft a response paragraph + LaTeX edits for one referee point
Full-reply mode: Generate a complete standalone reply LaTeX document

Examples

/respond-to-referee referee2.md point 3 -- address a specific point from a referee file
/respond-to-referee referee2.md -- generate complete reply to all points in the file
/respond-to-referee identification -- address a point by topic keyword

Input

The user provides:

A referee report file (markdown or text)
Either a specific point number, a topic keyword, or no argument (full reply)

Core Principles

These principles, distilled from journal editor guidelines and published advice (Noble 2017, PLOS Comp Bio; Review of Finance "Tips for Authors"), govern all referee responses.

Tone

Grateful but not obsequious: "We thank the referee for this suggestion" (good) vs. "We are deeply grateful for this invaluable insight" (too much)
Accept blame for misunderstandings: If the referee misread something, it is our exposition failure. "We realize our original text was ambiguous and have revised it as follows..."
Never dismissive: No bare "we respectfully disagree." Every disagreement must be backed by evidence, data, or a reference.
Direct answers first: Start each response with what you did ("We have added...", "We agree and now show..."), then explain why.
Remember the audience: You are writing to the editor, not (only) the referee.

Structure

Respond to every point: No exceptions, including minor ones.
Self-contained responses: Quote or paraphrase the revised manuscript text directly in the letter.
Reference by section name: Not page numbers (which shift between drafts).
Group related points: When two comments address the same underlying issue, respond jointly.

Substance

Do what the referee asks, even if you disagree: Run the requested analysis, report results in the letter, then explain why you believe the main text should differ.
Don't over-revise: Restrict changes to what is requested.
Address general criticisms globally: If the referee cites two examples, fix the problem paper-wide.

Read the full file on GitHub · 201 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 · 201 lines · 24 tokens per session scan A 918de47e0bc4

Subscribe to this mod's changes

respond-to-referee is a skill published in the GitHub repository Alexander-M-Dickerson/ai-asset-pricing (59 stars, last pushed 6mo ago), licensed MIT. It adds 24 tokens to every session and 1,728 once invoked, about $0.0001 per session on Opus 5.5. 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.

Scientific Writing and docs

respond-to-referee next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
respond-to-refereeAlexander-M-Dickerson/ai-asset-pricing	Skill	59	6mo ago	MIT	A	24	Claude Code
instrument-data-to-allotropeanthropics/knowledge-work-plugins	Skill	35k	2d ago	Apache-2.0	A	123	Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	83	Claude Code
matlabK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	44	Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	71	Claude Code, Codex
research-engineerdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	43	Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmed	Skill	5.8k	yesterday	Apache-2.0	A	205	Claude Code

ai-asset-pricing: Skill for Claude Code