agentmods.dev

CustomerNewsletter: Skill for Claude Code

.github/skills/curator-notes/SKILL.md

curator-notes is a skill for Claude Code, Codex from briancl2/CustomerNewsletter. It costs 96 tokens per session (1,797 once invoked), scanned A, original, MIT.

A newsletter-pipeline step that turns a curator’s monthly notes—such as rough links, text hints, and priorities—into organized content and editorial signals. Editorial signals are guidance about importance, themes, or internal context.

In plain words
What is it for?
Use it to process curator notes between discovery and newsletter curation, producing processed items and editorial guidance.
Why use it?
It turns an informal brain dump into material that later newsletter selection can use, while filtering private or internal links appropriately.

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 →

not rated 11repo 5mo ago A scan 96 tokens original MIT
View source ↗ briancl2/CustomerNewsletter briancl2.github.io
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/curator-notes/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 curator-notes

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/briancl2/customernewsletter/curator-notes"><img src="https://agentmods.dev/badge/skills/briancl2/customernewsletter/curator-notes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,797 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 $0.00096 $0.01797
Opus 5.5 $0.00038 $0.00719
Sonnet 5.5 $0.00019 $0.00359
Haiku 4.5 $0.00010 $0.00180

Measured 2mo ago against content hash d1c6d5a81759, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

curator-notes 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 2mo 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/skills/curator-notes/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Curator Notes Processing

Process the human curator's monthly notes file into pipeline-ready content and editorial signals.

Quick Start

  1. Check for workspace/curator_notes_YYYY-MM.md (or known variants)
  2. If no file exists, skip this phase entirely -- pipeline continues normally
  3. Parse and classify every item using the link type taxonomy
  4. Filter: internal links become editorial signals; public links get visited
  5. Output processed items + editorial signals
  6. Items feed into Phase 3 curation alongside Phase 1C discoveries

Inputs

  • Curator notes file (optional): workspace/curator_notes_YYYY-MM.md
    • May also appear as: workspace/<month>.md, workspace/<Month>.md, workspace/Jan.md, etc.
    • Check for any .md file in workspace/ that looks like a brain dump of links
  • Phase 1C Discoveries: For cross-reference (avoid duplicates)

Output

  • workspace/curator_notes_processed_YYYY-MM.md -- Items in universal extraction format, ready for Phase 3
  • workspace/curator_notes_editorial_signals_YYYY-MM.md -- Priority hints, theme suggestions, internal context

Core Workflow

Step 0: Locate the Notes File

Check these paths in order:

  1. workspace/curator_notes_YYYY-MM.md (canonical)
  2. workspace/<Month>.md (e.g., workspace/Jan.md, workspace/February.md)
  3. Any .md file in workspace/ containing 3+ URLs that isn't a pipeline output

If no file found: SKIP. Output nothing. Pipeline continues.

Step 1: Parse and Classify

For each line/item in the notes file, classify into one of these types:

Type Detection Pattern Action
GitHub Changelog github.blog/changelog/ PROCESS: visit URL, extract item
GitHub Blog github.blog/news-insights/ or github.blog/ai-and-ml/ PROCESS: visit URL, extract item
VS Code Release Notes code.visualstudio.com/updates/ PROCESS: visit URL, extract features
Microsoft DevBlog devblogs.microsoft.com/ PROCESS: visit if GitHub-specific
Community resource github.com/<user>/, personal sites, awesome-lists PROCESS: visit URL, extract description
VS Code extension marketplace.visualstudio.com/ PROCESS: visit URL, extract description
YouTube video youtube.com/watch, youtu.be/ PROCESS: visit, extract title and context
Event registration registration.goldcast.io/, github.com/resources/events/ PROCESS: extract event details
Named feature hint Text line without URL referencing a product name SIGNAL: flag as editorial priority
Internal link github.slack.com/, docs.google.com/, github.com/github/ (private repos), thehub.github.com/ SIGNAL: translate topic to public reference
Industry content hbr.org/, substack.com/, medium.com/, martinfowler.com/, analyst reports SIGNAL: framing context only
Competitor content blog.cloudflare.com/, sonarsource.com/, etc. SIGNAL: competitive context only
Text note (vague) Bare text, no URL, no product name SIGNAL: note for context

Read the full file on GitHub · 160 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. 2mo ago First seen · 160 lines · 96 tokens per session scan A d1c6d5a81759

Subscribe to this mod's changes

curator-notes is a skill published in the GitHub repository briancl2/CustomerNewsletter (11 stars, last pushed 5mo ago), licensed MIT. It adds 96 tokens to every session and 1,797 once invoked, about $0.0004 per session on Opus 5.5. 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.

Marketing and SEOWriting and docsagentic-workflowsagentscopilotllmopsmkdocsnewsletter
Related

curator-notes compared with skills from other repositories

curator-notes next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
curator-notesbriancl2/CustomerNewsletterSkill115mo agoMITA96Claude Code, Codex
trulens-diagnosistruera/trulensSkill3.6kyesterdayMITA17Claude Code, Codex
agents-sdk-dotnet-activityhandler-migrationmicrosoft/AgentsSkill1.1kyesterdayMITA76Claude Code
agents-sdk-dotnetmicrosoft/AgentsSkill1.1kyesterdayMITA112Claude Code
agents-sdk-typescript-otelmicrosoft/AgentsSkill1.1kyesterdayMITA88Claude Code
bf-to-agents-sdk-dotnet-migrationmicrosoft/AgentsSkill1.1kyesterdayMITA56Claude Code
github-review-prfeiskyer/claude-code-settingsSkill1.7kyesterdayMITA90Claude Code