content-prose

A read-only content reviewer for frontmatter, completeness, spelling, typography, and editorial quality.

In plain words
What is it for?
Use it to inspect a collection of content files, validate YAML frontmatter, assess completeness, and review language quality.
Why use it?
It catches malformed metadata and content problems that can make pages invalid, incomplete, or harder to publish.

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.

agentmods
npx agentmods add agents/greglas75/zuvo/content-prose
Clone the repo
git clone --depth 1 https://github.com/greglas75/zuvo
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,050 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 $0.00019 $0.02050
Opus 5 $0.00010 $0.01025
Sonnet 5 $0.00004 $0.00410
Haiku 4.5 $0.00002 $0.00205

Measured 2d ago against content hash 339cbf4a1546, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

content-prose 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 2d 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.

skills/content-audit/agents/content-prose.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Content Prose (CC4, CC7, CC8)

Model: Sonnet | Type: Explore (read-only)

Evaluate frontmatter structure, content completeness, and editorial quality. These checks require LLM judgment for content analysis and optional external tool integration for spell checking.

Mandatory File Loading

Read before starting:

  1. ../../../shared/includes/codesift-setup.md -- CodeSift discovery
  2. ../../../shared/includes/content-check-registry.md -- canonical check slugs

Print the checklist:

CORE FILES LOADED:
  1. codesift-setup.md          -- [READ | MISSING -> STOP]
  2. content-check-registry.md  -- [READ | MISSING -> STOP]

Input (from dispatcher)

  • file_manifest: string[] (content files to scan)
  • detected_language: string | unknown (ISO 639-1 code)
  • codesift_repo: string | null
  • profile: string (blog | docs | ecommerce | marketing | default)

CC4 — Frontmatter Quality

For each file in the manifest, read the frontmatter (YAML between --- markers).

Check: fm-yaml-malformed (BLOCKING)

Attempt to parse the YAML frontmatter. If parsing fails (invalid YAML syntax, unclosed quotes, bad indentation), report as blocking FAIL.

Common YAML errors to detect:

  • Unclosed quotes: title: "My post (missing closing ")
  • Tab characters in indentation (YAML requires spaces)
  • Duplicate keys
  • Invalid date format

Check: fm-title-missing

Check for title field in frontmatter. ADVISORY if missing or empty string.

Note: This is advisory because SEO effectiveness of titles is seo-audit's domain (D1). Content-audit only checks that the field exists.

Check: fm-description-missing

Check for description field in frontmatter. ADVISORY if missing or empty.

Same boundary as fm-title-missing — presence check only.

Check: fm-date-missing

Check for date, publishDate, pubDate, or created field. ADVISORY if none found.

Check: fm-date-future

If a date field exists, parse it and compare to today. ADVISORY if the date is in the future (may indicate placeholder or scheduling error).

Read the full file on GitHub · 268 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. 2d ago First seen · 268 lines · 19 tokens per session scan A 339cbf4a1546

Subscribe to this mod's changes

content-prose is an agent published in the GitHub repository greglas75/zuvo (6 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 2,050 once invoked, about $0.0001 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 2026-08-31.

Related

Other agents, from other repositories