CustomerNewsletter: Skill for Claude Code

.github/skills/newsletter-validation/SKILL.md

newsletter-validation is a skill for Claude Code, Codex from briancl2/CustomerNewsletter. It costs 57 tokens per session (1,770 once invoked), scanned A, original, MIT.

A quality-check workflow for a completed newsletter. It runs automated checks on required sections, link formatting, forbidden wording, and structural rules, then supports a manual review.

In plain words
What is it for?
Use it after assembly to validate a Markdown newsletter, inspect failures, fix the file, and run the checks again.
Why use it?
It catches missing sections, invalid links, unwanted patterns, and customer-facing process details before publication. A successful check returns exit code 0; a failed check returns exit code 1 with details.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is briancl2/CustomerNewsletter's own configuration. It tells Claude Code and Codex how to work on CustomerNewsletter itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CustomerNewsletter configures →

Reuse

Borrowing it

Nothing to install: this file belongs to briancl2/CustomerNewsletter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/briancl2/CustomerNewsletter/main/.github/skills/newsletter-validation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/briancl2/CustomerNewsletter

Made for: Claude Code, Codex.

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 newsletter-validation

README.md
[![agentmods](https://agentmods.dev/badge/skills/briancl2/customernewsletter/newsletter-validation/github.svg)](https://agentmods.dev/skills/briancl2/customernewsletter/newsletter-validation)
Your own site
<a href="https://agentmods.dev/skills/briancl2/customernewsletter/newsletter-validation"><img src="https://agentmods.dev/badge/skills/briancl2/customernewsletter/newsletter-validation/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.

agentmods 80×15 button for newsletter-validation

Your own site · 80×15
<a href="https://agentmods.dev/skills/briancl2/customernewsletter/newsletter-validation"><img src="https://agentmods.dev/badge/skills/briancl2/customernewsletter/newsletter-validation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,770 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.01770
Opus 5 $0.00028 $0.00885
Sonnet 5 $0.00011 $0.00354
Haiku 4.5 $0.00006 $0.00177

Measured 12d ago against content hash b73c55fbb169, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

newsletter-validation 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate_newsletter.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/newsletter-validation/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Newsletter Validation

Validate newsletter output against quality standards.

Quick Start

  1. Run automated validation: bash .github/skills/newsletter-validation/scripts/validate_newsletter.sh <newsletter_file>
  2. Review results: exit 0 = pass, exit 1 = fail with details
  3. If automated checks pass, perform manual review using the rubric
  4. Fix any issues and re-validate

Inputs

  • Newsletter file: Path to the assembled newsletter markdown (e.g., output/YYYY-MM_month_newsletter.md)

Output

  • Exit code 0 (pass) or 1 (fail) with detailed report on stdout

Automated Checks

The validate_newsletter.sh script checks:

Required Sections

  • Introduction with archive link
  • Copilot section with Latest Releases
  • Copilot at Scale with changelog links
  • Events section with YouTube playlists
  • Closing section

Forbidden Patterns

  • Raw URLs not in markdown links
  • Em dashes
  • Double-bracket links [[
  • Copilot Free/Individual/Pro/Pro+ plan mentions
  • Wikilink format
  • Customer-facing Copilot App release-process leakage (github/github-app, anonymous fetch/404, private tags, authenticated release notes, [truncated])
  • Legal/CCC content outside the active Enterprise/Security/Governance/Legal/Compliance heading path unless the issue is explicitly legal-led
  • VS Code body-prose sequences with 3+ 1.xxx version numbers
  • Under-linked release-inventory bullets for Copilot App and high-volume Copilot CLI, using generic release-count/release-stream triggers rather than one month-specific count
  • Specific-labeled inline links that point to a generic landing page instead of the deep/anchored source (WARN; see Link Specificity)

Link Specificity (Inline Deep-Link Policy)

Applies to inline contextual links in prose -- a link whose label names a specific feature, capability, or claim. Such a link must point to the most specific source that documents that exact thing: a section anchor, a dated changelog post, or a deep doc page. It must not point to a generic landing page, a bare version page, or a blog root.

Read the full file on GitHub · 120 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 120 lines · 57 tokens per session scan A b73c55fbb169

Subscribe to this mod's changes

newsletter-validation is a skill published in the GitHub repository briancl2/CustomerNewsletter (11 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 1,770 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 2026-08-30.