copy-review

copy-review is a command for coding agents from SaigonXIII/evc. It costs 32 tokens per session (1,172 once invoked), scanned A, original, MIT.

A copy checker for marketing text on platforms such as X, LinkedIn, blogs, email, websites, decks, and ads. It compares the text with brand voice, legal requirements, and platform-specific writing rules.

In plain words
What is it for?
Use it to review pasted text or a file and get a scored audit with suggested fixes.
Why use it?
It finds tone problems, banned wording, missing disclaimers, and format issues before the copy is published.

Command

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 commands/saigonxiii/evc/copy-review
Clone the repo
git clone --depth 1 https://github.com/SaigonXIII/evc

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 copy-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/saigonxiii/evc/copy-review.svg)](https://agentmods.dev/commands/saigonxiii/evc/copy-review)
Your own site
<a href="https://agentmods.dev/commands/saigonxiii/evc/copy-review"><img src="https://agentmods.dev/badge/commands/saigonxiii/evc/copy-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,172 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00032 $0.01172
Opus 5 $0.00016 $0.00586
Sonnet 5 $0.00006 $0.00234
Haiku 4.5 $0.00003 $0.00117

Measured 5d ago against content hash 75eff6cad08d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

copy-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 5d 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.

_templates/commands/copy-review.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copy Review

Review marketing copy against brand voice guidelines, legal guardrails, and platform-specific rules. Complements /content-review (canon compliance) with voice, legal, and format checks.

Usage

/copy-review [platform]

[Paste copy here, or provide a file path]

Platforms: x, linkedin, blog, deck, email, website, ad

Steps

1. Load Brand Voice Config

Read the brand voice configuration:

{{CONFIG_DIR}}/brand-voice.json

If unavailable, fall back to canon rules:

{{CONFIG_DIR}}/canon-rules.json

Extract:

  • Brand voice pillars (e.g. authoritative, technical, approachable)
  • Tone-of-voice rules per content pillar
  • Banned words and phrases
  • Required terminology
  • Legal disclaimers required by platform

2. Read the Submitted Copy

Read the full piece. If it's a file path, read it. If pasted inline, use as-is.

3. Brand Voice Audit

Check the copy against each voice pillar:

Tone Check
  • Does the copy match the configured brand voice?
  • Is it consistent throughout (no tone shifts mid-piece)?
  • Is the register appropriate for the platform?
    • X: concise, punchy, no corporate speak
    • LinkedIn: professional but not stiff, thought-leadership tone
    • Blog: educational, infrastructure-credible, human
    • Deck: confident, data-backed, outcome-focused
    • Email: direct, warm, action-oriented
Terminology Check
  • Uses approved product names and descriptions from required_language in canon
  • No {{DEFUNCT_REFERENCE}} references
  • Only {{PROOF_POINT_1}} + {{PROOF_POINT_2}} as proof points
  • All required phrasings used correctly (check required_language dict in brand/canon-rules.json)
  • Any numerical claims match canon figures exactly
Legal Guardrails
  • No guaranteed returns language ("guaranteed yield", "risk-free", "assured returns")
  • No unsubstantiated superlatives ("the best", "the only", "the first") unless provably true
  • No forward-looking statements without qualification
  • No competitor disparagement by name
  • Financial claims have appropriate disclaimers
  • No misleading comparisons
  • Regulatory-sensitive terms flagged (varies by jurisdiction)

Read the full file on GitHub · 170 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. 5d ago First seen · 170 lines · 32 tokens per session scan A 75eff6cad08d

Subscribe to this mod's changes

copy-review is a command published in the GitHub repository SaigonXIII/evc (56 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 1,172 once invoked, about $0.0002 per session on Opus 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.