content-review

content-review is a command for coding agents from SaigonXIII/evc. It costs 30 tokens per session (1,024 once invoked), scanned A, original, MIT.

A checker for written content against a brand's central rules, called a brand canon. It reviews posts, slides, emails, website text, proposals, and other copy for wording and positioning problems.

In plain words
What is it for?
Use it on pasted text, a file, or a Google Doc link to receive a scored review and suggested corrections.
Why use it?
It catches banned phrases, generic marketing language, inconsistent framing, and mismatches with the intended audience before publication.

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/content-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 content-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/saigonxiii/evc/content-review.svg)](https://agentmods.dev/commands/saigonxiii/evc/content-review)
Your own site
<a href="https://agentmods.dev/commands/saigonxiii/evc/content-review"><img src="https://agentmods.dev/badge/commands/saigonxiii/evc/content-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,024 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 $0.00030 $0.01024
Opus 5 $0.00015 $0.00512
Sonnet 5 $0.00006 $0.00205
Haiku 4.5 $0.00003 $0.00102

Measured 5d ago against content hash 52d9e98e6e4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

content-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/content-review.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Review

Audit any piece of copy against the brand canon defined in brand/canon-rules.json. Works on LinkedIn posts, deck slides, email copy, website text, proposals, or any other written asset.

Usage

/content-review

[Paste copy here, or provide a file path / Google Doc URL]

Steps

1. Load the brand canon

Read the authoritative rules file:

brand/canon-rules.json

Extract and hold in memory:

  • banned_phrases[] — the full list with reasons
  • framing_red_flags[] — phrases that signal lazy or generic marketing language
  • required_language.* — product_name, company_anchor, and any other fields the user has set
  • usps[] — the product's unique selling points (exact wording)
  • defunct_partners[] — names that must never appear
  • audience — the intended buyer/reader
  • positioning — the one-line positioning statement
  • compliance_rules[<jurisdiction>] — for any jurisdiction set in config.env → COMPLIANCE_JURISDICTIONS

If any field is empty or missing, note it and proceed with what's available — do not invent rules.

Also read content-engine/config.md if it exists for audience segments and tone guidance.

2. Read the submitted copy

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

3. Run the audit

Check every claim, phrase, and framing decision against the loaded canon. For each issue found, note:

  • The exact offending text
  • The specific canon rule it violates (quote the rule)
  • A suggested replacement that aligns with the canon
Banned phrases (automatic fail)

Match against banned_phrases[] in canon-rules.json. For each hit, cite the reason field verbatim.

Defunct references (automatic fail)

Match against defunct_partners[]. These are names that were once valid but no longer are — they must never appear in new content.

Framing red flags (flag and explain)

Match against framing_red_flags[]. These are lazy/generic phrases ("best in class", "revolutionary", etc.) — the user's canon may extend this list for their category.

Read the full file on GitHub · 123 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 · 123 lines · 30 tokens per session scan A 52d9e98e6e4c

Subscribe to this mod's changes

content-review is a command published in the GitHub repository SaigonXIII/evc (56 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 1,024 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.