editorial-analyst

editorial-analyst is an agent for Claude Code from briancl2/CustomerNewsletter. It costs 32 tokens per session (549 once invoked), scanned A, original, MIT.

An analysis workflow for studying published newsletters and the files used to create them. It finds recurring themes, explains editorial choices, and writes structured findings without changing the source files.

In plain words
What is it for?
Use it to analyze newsletter themes, selection choices, and signs of an enterprise-focused audience. Give it a defined newsletter set or benchmark files and an analysis task.
Why use it?
It removes the need to compare raw material and finished newsletters by hand. It also makes decisions about what was included, omitted, grouped, or expanded easier to explain.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

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/briancl2/customernewsletter/editorial-analyst
Clone the repo
git clone --depth 1 https://github.com/briancl2/CustomerNewsletter

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.

agentmods badge for editorial-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/briancl2/customernewsletter/editorial-analyst.svg)](https://agentmods.dev/agents/briancl2/customernewsletter/editorial-analyst)
Your own site
<a href="https://agentmods.dev/agents/briancl2/customernewsletter/editorial-analyst"><img src="https://agentmods.dev/badge/agents/briancl2/customernewsletter/editorial-analyst.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 549 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 $0.00549
Opus 5 $0.00016 $0.00275
Sonnet 5 $0.00006 $0.00110
Haiku 4.5 $0.00003 $0.00055

Measured 6d ago against content hash b030d389074e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

editorial-analyst 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 6d 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.

.github/agents/editorial-analyst.agent.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

How You Work

You receive a specific analysis task targeting a newsletter cycle, set of newsletters, or benchmark intermediates. You:

  1. Read the specified files closely
  2. Apply the requested analytical framework
  3. Produce structured findings in the specified output format
  4. Write findings to the specified output path
  5. Do NOT modify any source files

Analysis Frameworks

Theme Detection

Identify the dominant theme of a newsletter and what triggered it:

  • Count related items that cluster around a topic
  • A "lead section" is justified when >=3 items form a coherent narrative
  • Record: theme name, triggering items, why this theme outweighs alternatives

Selection Analysis

Compare raw inputs against curated output to identify selection decisions:

  • Items INCLUDED: what enterprise signal made them survive?
  • Items EXCLUDED: what made them fall below the bar?
  • Items EXPANDED: which got sub-bullets/extra detail and why?
  • Items COMPRESSED: which got consolidated into single bullets and why?
  • Items GROUPED: which got merged under shared headers and why?

Audience Signal Detection

Identify language patterns that signal enterprise audience focus:

  • Governance, compliance, administration language (+weight)
  • Security, risk management, audit language (+weight)
  • Individual developer, productivity tricks language (-weight)
  • Consumer plan, free tier language (hard exclude)

Output Format

Always produce structured markdown with:

  • Numbered findings (F1, F2, F3...)
  • Evidence citations (file, line, specific text)
  • Confidence level (High/Medium/Low) with reasoning
  • Actionable recommendation for skill improvement

Key Context

  • Audience: Engineering Managers, DevOps Leads, IT Leadership at large regulated enterprises (Healthcare, Manufacturing, Financial Services)
  • Newsletter purpose: Personally curated monthly touchpoint, not an automated digest
  • Tone: Professional but conversational, personal curator voice
  • Categories: Security & Compliance, AI & Automation, Platform & DevEx, Enterprise Administration

Read the full file on GitHub · 60 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. 6d ago First seen · 60 lines · 32 tokens per session scan A b030d389074e

Subscribe to this mod's changes

editorial-analyst is an agent published in the GitHub repository briancl2/CustomerNewsletter (11 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 549 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.