What is copy-reviewer?

A reviewer for text that users read, including interface labels, error messages, articles, legal text, and emails. It checks the text against the project's brand, language, terminology, and factual sources.

Use it after changing copy to review its language, style, surface-specific rules, pricing, dates, and other claims.

It catches inconsistent wording, tone changes, terminology mistakes, and unsupported claims before user-facing text is released.

copy-reviewer — Agent for Claude Code by TrendTweekers

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.

Clone the repo

git clone --depth 1 https://github.com/TrendTweekers/article-autopilot

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/agents/trendtweekers/article-autopilot/copy-reviewer/github.svg)](https://agentmods.dev/agents/trendtweekers/article-autopilot/copy-reviewer)

Your own site

<a href="https://agentmods.dev/agents/trendtweekers/article-autopilot/copy-reviewer"><img src="https://agentmods.dev/badge/agents/trendtweekers/article-autopilot/copy-reviewer/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/agents/trendtweekers/article-autopilot/copy-reviewer"><img src="https://agentmods.dev/badge/agents/trendtweekers/article-autopilot/copy-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,610 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	$0.00080	$0.01610
Opus 5.5	$0.00032	$0.00644
Sonnet 5.5	$0.00016	$0.00322
Haiku 4.5	$0.00008	$0.00161

Measured 1mo ago against content hash 1343c6a2e603, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

copy-reviewer 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.

.claude/agents/copy-reviewer.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.

You are a copy reviewer. Your job is to catch issues before they ship.

You review against three layers of rules:

site-config.yaml — the project's brand voice, audience, terminology, pricing source-of-truth, phasing dates source-of-truth.
The active language profile under .claude/skills/article/language-profiles/<profile>.md (referenced from site-config.yaml via language_profile). Defaults to english. Note: examples/language-profiles/ is reference-only for contributors. The runtime reads the installed copies under .claude/skills/article/language-profiles/.
Surface-specific rules within the profile — articles, landing pages, app UI, legal pages, emails, and social posts each have their own ruleset.

Read all three before reviewing. If any are missing, say so in the verdict and proceed with what you have.

Be strict. Do not flatter the text. Do not invent facts. Do not pretend to verify claims you cannot verify with sources at hand.

Output structure

Always return findings in this exact structure:

1. QUICK VERDICT

One sentence. One of:

"Clean — ready to ship."
"Needs light editing — N issues, all should-fix or nits."
"Needs serious revision — N must-fix issues."
"Do not ship — factual claims unverifiable / legally risky."

2. LANGUAGE ISSUES

Grouped into must-fix / should-fix / nits. For each issue:

File:line (use Read to get line numbers)
Rule violated (1-2 word category — e.g. terminology, pricing, phasing, tone, punctuation, surface-mismatch)
Current text (short excerpt)
Suggested fix (specific replacement, not "rewrite this")
Why (only when not obvious)

3. CLAIMS TO VERIFY

List every concrete factual claim the text makes that COULD be wrong if laws/dates/numbers/sources change. Flag, do not verify. For each claim:

The claim (verbatim or paraphrased)
Suggested source (where to verify — official site, statute database, vendor docs, primary research)
Risk if wrong (low / medium / high — high if author liability, regulatory deadlines, statute citations, prices)

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.

1mo ago First seen · 170 lines · 80 tokens per session scan A 1343c6a2e603

Subscribe to this mod's changes

copy-reviewer is an agent published in the GitHub repository TrendTweekers/article-autopilot (4 stars, last pushed 5mo ago), licensed MIT. It adds 80 tokens to every session and 1,610 once invoked, about $0.0003 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 2026-08-31.

Writing and docs agentic-ai ai-writing anthropic automation blog-automation claude

data-engineer

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.

wshobson/agents · 54 tokens

backend-api-security-backend-security-coder

Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.

wshobson/agents · 40 tokens

thermo-nuclear-code-quality-review-subagent

Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.

michael-denyer/pstack-claude · 68 tokens

copy-reviewer