cold-review

cold-review is a skill for Claude Code, Codex from petar-djukic/writing-skills. It costs 0 tokens per session (870 once invoked), scanned A, original, MIT.

A fresh-context review that compares a draft with its original text to find changes in meaning. It reports whether to keep the draft, restore specific original passages, or reject it, rather than writing new prose.

In plain words
What is it for?
It is for checking rewritten documents for factual and meaning drift before publication.
Why use it?
It catches reversed claims, misplaced numbers, changed quotations, and weakened statements that can be missed during editing.

Skill for Claude CodeCodex

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

Good fit It is for checking rewritten documents for factual and meaning drift before publication.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/petar-djukic/writing-skills/cold-review
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 petar-djukic/writing-skills --skill cold-review
Clone the repo
git clone --depth 1 https://github.com/petar-djukic/writing-skills

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 cold-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/petar-djukic/writing-skills/cold-review/github.svg)](https://agentmods.dev/skills/petar-djukic/writing-skills/cold-review)
Your own site
<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/cold-review"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/cold-review/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 cold-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/cold-review"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/cold-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 870 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 $0.00870
Opus 5 $0.00000 $0.00435
Sonnet 5 $0.00000 $0.00174
Haiku 4.5 $0.00000 $0.00087

Measured 7d ago against content hash 137f88bd5c5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cold-review 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 7d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/cold_review.py, scripts/test_cold_review.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/cold-review/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: cold-review description: >- Fresh-context entailment check with a fixed contract: a reviewer that never saw the drafting conversation reads baseline + candidate, paragraph-aligned, hunting inverted claims, numbers reattached to wrong claims, altered quotations, and hedges that change assertions; verdicts limited to ship as-is / ship with listed verbatim-reverts / reject. Every accepted fix is a revert to the baseline span — no authored prose. Ships a mechanical drift screen and a revert applier with invariant re-checks. Triggers: cold review, cold read the candidate, entailment check, fresh-context review, did the rewrite change the meaning, revert list. argument-hint: 'screen|apply --baseline <b.md> --candidate <c.md>'

Cold Review (fresh-context entailment, reverts only)

Every generative stage measured against a cold read lost most of its raw gain there, and the two 2026-09-01 runs that fixed this contract caught real damage both times: swapped 0.768/0.867 arm numbers, an inverted improvement direction, a lost constitution bridge sentence — and, on the second run, confirmed ship-as-is with zero reverts, which is also a result. The prompt was re-improvised per run; now it is versioned.

The contract

  • Fresh context, maker is not checker. The reviewer sees only the baseline, the candidate, the caller's named high-value targets, the constitution's [CHECK] items when the form has one, and the mechanical screen's findings. Never the rewrite history, reasoning, or diffs.
  • Meaning entailment, paragraph by paragraph: inverted claims, numbers reattached to wrong claims, altered quotations (including reattributed judgment), hedges that change assertions, [CHECK] items no longer satisfied.
  • Closed verdict vocabulary: ship as-is | ship with reverts: p<N>: <damage> | reject candidate: <why>. The reviewer never proposes prose.
  • The repair rule: every accepted fix is a verbatim revert to the baseline span — kept-original at paragraph level, no authored prose. Damage that reverts cannot save (structural) rejects the candidate.

Read the full file on GitHub · 77 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 77 lines · 0 tokens per session scan A 137f88bd5c5f

Subscribe to this mod's changes

cold-review is a skill published in the GitHub repository petar-djukic/writing-skills (4 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 870 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 2026-09-05.

Related

Other skills, from other repositories

humanizer

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…

NulightJens/humanizer-stack · 111 tokens

structural-humanizer

Remove the discourse-level (structural) signs of AI writing that survive surface editing: stated lessons and moral-of-the-story closers, tidy single-track arcs, embodied-emotion performance ("chest tightened"), vague allusions instead of named references, unbroken linear structure, and shape convergence across pieces.…

NulightJens/humanizer-stack · 188 tokens

story-import

A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.

zenstory-ai/oh-story-claudecode · 98 tokens

story-review

A review workflow for finding story problems from several viewpoints, including issues with structure, characters, wording, and fictional world rules. It can use multiple reviewer agents or work alone.

zenstory-ai/oh-story-claudecode · 74 tokens

story-long-analyze

A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.

zenstory-ai/oh-story-claudecode · 173 tokens

story-deslop

A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.

zenstory-ai/oh-story-claudecode · 62 tokens