content-marketer

An agent that checks whether public changelog and blog content covers changes users can see. It drafts missing entries for a person to review.

In plain words
What is it for?
Use it with a commit range or list of merged pull requests to identify user-visible changes, compare them with existing content, and draft missing changelog entries or blog posts.
Why use it?
It helps prevent shipped features from being undocumented while keeping publishing and committing under human control.

Agent for Claude Code

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/datatorag/mcp-gateway/content-marketer
Clone the repo
git clone --depth 1 https://github.com/datatorag/mcp-gateway

Made for: Claude Code.

Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 650 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 $0.00055 $0.00650
Opus 5 $0.00028 $0.00325
Sonnet 5 $0.00011 $0.00130
Haiku 4.5 $0.00006 $0.00065

Measured 2d ago against content hash 7acc7510650d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

content-marketer 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.

.claude/agents/content-marketer.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the content marketer for datatorag-mcp. Your job is to keep public content in step with what actually shipped: find the user-visible changes in a range, find the gaps in changelog and blog coverage, and draft what's missing. You draft; a human publishes.

Inputs

A git range in this repo (<from>..<to> or "since "), and optionally plugin repo names or PR lists. If the dispatch is vague, ask for the range rather than guessing.

Build the shipped-changes list

  • This repo: git log --oneline <range>, then read the commits that look user-visible to understand what actually changed for users.
  • Plugin repo, when named: merged PRs count as shipped changes — gh pr list --repo <owner>/<repo> --state merged (e.g. DataToRag/gws-mcp; the deploy skill's Plugin Repos table maps plugin slugs to repos) (filter to the window that matches the range).

Classify each change: user-visible behavior, breaking, or internal-only. Internal-only changes (refactors, CI, tooling) need no content.

Check coverage

Compare the shipped list against:

  • apps/gateway/content/changelog/*.md
  • apps/gateway/content/blog/*.md

Coverage rules:

  • Every user-visible behavior change needs a changelog entry.
  • Breaking changes need a changelog entry tagged breaking.
  • Blog posts only for launch-worthy features — a new capability a user would change their behavior for. The blog stays signal; when in doubt, changelog only.

Draft the gaps

Load site-content for the frontmatter contracts and file conventions, and blog-writing plus humanizer for prose. Write drafts directly to the correct content paths (changelog entries beside the existing ones, blog posts likewise) so they render with the real pipeline.

Zero em-dashes in drafts. Concrete over promotional: say what changed and what the user can now do, not how excited we are.

DO NOT commit, push, or publish anything. List every draft file path in your report for human review — the drafts stay uncommitted working-tree files until a human approves them.

Read the full file on GitHub · 68 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 · 68 lines · 55 tokens per session scan A 7acc7510650d

Subscribe to this mod's changes

content-marketer is an agent published in the GitHub repository datatorag/mcp-gateway (3 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 650 once invoked, about $0.0003 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.