agentmods.dev

address-reviewer-comment

address-reviewer-comment is a skill for Claude Code, Codex from Rezenders/scientific_writing_agent. It costs 37 tokens per session (755 once invoked), scanned A, original, Apache-2.0.

A review-response workflow for changing manuscript text in response to a specific reviewer comment. A manuscript is a paper being prepared for publication, and the workflow creates and checks possible revisions before changing the file.

In plain words
What is it for?
Use it when a reviewer targets a paragraph or section and you need candidate rewrites, scientific and consistency checks, and a refined response.
Why use it?
It helps answer reviewer concerns while preserving the surrounding meaning and consistency of the paper, without editing the file before approval.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

not rated 14repo changed 1mo ago A scan 37 tokens original Apache-2.0

Good fit Use it when a reviewer targets a paragraph or section and you need candidate rewrites, scientific and consistency checks, and a refined response.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rezenders/scientific_writing_agent/address-reviewer-comment
View source ↗ Rezenders/scientific_writing_agent
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.

Any agent
npx skills add Rezenders/scientific_writing_agent --skill address-reviewer-comment
Clone the repo
git clone --depth 1 https://github.com/Rezenders/scientific_writing_agent

Made for: Claude Code, Codex.

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 address-reviewer-comment

README.md
[![agentmods](https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/address-reviewer-comment/github.svg)](https://agentmods.dev/skills/rezenders/scientific_writing_agent/address-reviewer-comment)
Your own site
<a href="https://agentmods.dev/skills/rezenders/scientific_writing_agent/address-reviewer-comment"><img src="https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/address-reviewer-comment/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 address-reviewer-comment

Your own site · 80×15
<a href="https://agentmods.dev/skills/rezenders/scientific_writing_agent/address-reviewer-comment"><img src="https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/address-reviewer-comment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 755 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 $0.00037 $0.00755
Opus 5.5 $0.00015 $0.00302
Sonnet 5.5 $0.00007 $0.00151
Haiku 4.5 $0.00004 $0.00076

Measured 1mo ago against content hash b29d683a7ea1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

address-reviewer-comment 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 1mo 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.

.agents/skills/address-reviewer-comment/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Address Reviewer Comment

Follow AGENTS.md. Use this workflow for a reviewer comment targeting a passage or section.

Inputs

Require the verbatim comment, target text and location, immediate context, and comment type when known. Record the intended response in a passage contract using .agents/context/passage-contract.md. After the author approves the interpretation, append or update a trace entry in .agents/context/reviewer-contracts.md.

The contract must distinguish:

  • what the reviewer correctly identifies
  • what the manuscript can support
  • what must not be conceded, claimed, or implied
  • how the revision should resolve the comment

The author approves this interpretation before drafting when the response strategy is not unambiguous.

Workflow

  1. Analyze the comment. Identify the challenged claim, missing information, or presentation defect. Search the manuscript for related statements. Check .agents/context/claim-ledger.md and .agents/context/do-not-say.md for relevant guardrails.
  2. Verify when needed. For technical or mixed comments, invoke .agents/agents/paper-implementation-checker.md. Stop on DIVERGES; carry CANNOT_VERIFY forward as an explicit limit.
  3. Confirm one direction. If more than one materially different response is defensible, present short strategy options with their tradeoffs and obtain the author's choice. Do not create full prose alternatives at this stage.
  4. Record the contract. Once the author approves the interpretation, append or update the response contract in .agents/context/reviewer-contracts.md using its template.
  5. Draft once. Invoke .agents/agents/writer.md with the approved contract and evidence to produce one revision proposal.
  6. Diagnose. Invoke .agents/agents/scientific-paper-reviewer.md for comment coverage and claim precision and .agents/agents/consistency-auditor.md for manuscript alignment. Use .agents/agents/argument-reviewer.md only when the response depends on a nontrivial inference. Critics report defects only and do not propose replacement prose.
  7. Obtain author decisions. Present the proposal and deduplicated findings. The author accepts, rejects, or modifies material findings before they reach the writer.
  8. Revise once if needed. Invoke writer with only accepted findings. Show a semantic diff, verify comment coverage and contract compliance, then stop. Begin another cycle only for a specific unresolved defect identified by the author.
  9. Edit only after approval. Apply the approved revision only under the edit-approval rule in AGENTS.md, then run a targeted diff review and the required validation.

Read the full file on GitHub · 60 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. 1mo ago Changed · -75 lines · -3 tokens per session b29d683a7ea1
  2. 2mo ago First seen · 135 lines · 40 tokens per session scan A 22a6891d3603

Subscribe to this mod's changes

address-reviewer-comment is a skill published in the GitHub repository Rezenders/scientific_writing_agent (14 stars, last pushed 17d ago), licensed Apache-2.0. It adds 37 tokens to every session and 755 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.

Writing and docs
Related

address-reviewer-comment compared with skills from other repositories

address-reviewer-comment next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
address-reviewer-commentRezenders/scientific_writing_agentSkill1417d agoApache-2.0A37Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code