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.
curl -O https://raw.githubusercontent.com/briancl2/CustomerNewsletter/main/.github/skills/newsletter-polishing/SKILL.mdgit clone --depth 1 https://github.com/briancl2/CustomerNewsletterWrote 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.
[](https://agentmods.dev/skills/briancl2/customernewsletter/newsletter-polishing)<a href="https://agentmods.dev/skills/briancl2/customernewsletter/newsletter-polishing"><img src="https://agentmods.dev/badge/skills/briancl2/customernewsletter/newsletter-polishing/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.
<a href="https://agentmods.dev/skills/briancl2/customernewsletter/newsletter-polishing"><img src="https://agentmods.dev/badge/skills/briancl2/customernewsletter/newsletter-polishing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.02172 |
| Opus 5.5 | $0.00030 | $0.00869 |
| Sonnet 5.5 | $0.00015 | $0.00434 |
| Haiku 4.5 | $0.00008 | $0.00217 |
Grade A, and why
newsletter-polishing 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Newsletter Polishing
Apply automated polishing rules to a Phase 4 newsletter, eliminating ~34% of manual post-publication edits.
Quick Start
- Read the Phase 4 newsletter from
output/YYYY-MM_month_newsletter.md - Apply Tier 1 structural fixes (zero-risk, deterministic)
- Apply Tier 2 content-aware fixes (normalization)
- Apply Tier 3 editorial guidelines (LLM-assisted)
- Validate the polished newsletter
- Write polished output back to
output/YYYY-MM_month_newsletter.md
Inputs
- Phase 4 Newsletter:
output/YYYY-MM_month_newsletter.md(required) - Polishing Intelligence:
reference/polishing-intelligence.md(context)
Output
- Polished Newsletter:
output/YYYY-MM_month_newsletter.md(overwrite in place) - Polishing report with changes applied
Core Workflow
Step 1: Tier 1 Structural Fixes (Zero-Risk)
Apply these deterministic fixes automatically. They eliminate formatting errors that appear in 34% of historical diffs.
| # | Rule | Action |
|---|---|---|
| 1 | Heading space | Insert space after # in headings: ###Title becomes ### Title |
| 2 | Bullet normalization | Replace •, * (non-bold), and ** (used as bullets) with - at top level |
| 3 | Unicode cleanup | Remove U+FFFC, U+200B, U+FEFF and other control characters |
| 4 | Double spaces | Collapse multiple spaces to single (except indentation) |
| 5 | Space before paren | Remove spaces before ) |
| 6 | Month abbreviations | Use 3-letter abbreviations in event dates: January to Jan, etc. |
| 7 | Heading hierarchy | Validate: no # headings after the lead section; ### must have a parent ## |
Step 2: Tier 2 Content-Aware Fixes
Apply these with review. They address naming consistency and label formatting.
| # | Rule | Action |
|---|---|---|
| 8 | Product name capitalization | Apply canonical dictionary (see product-names.md). Common fixes: coding agent to Coding Agent, agent mode to Agent Mode, copilot spaces to Copilot Spaces |
| 9 | Status label format | Normalize to (`GA`) and (`PREVIEW`). Never nest bold inside backticks. Remove inconsistent formats like (GA), (**GA**), (Preview) |
| 10 | Link syntax validation | Verify all [text](url) render correctly. No broken ]( patterns, no double brackets [[text]](url) unless intended |
| 11 | Chronological event sorting | Sort virtual and in-person events by date ascending |
| 12 | Sub-bullet format | Convert inline paragraphs under bullets to nested - sub-bullets. Max 3 sub-bullets per parent |
| 12b | Link label audit | Verify link labels match URL-to-label mapping: github.blog/changelog/ = [Changelog] (never [Announcement]), github.blog/news-insights/ = [GitHub Blog] (never [CPO Blog]), code.visualstudio.com/updates = [Release Notes]. No internal role titles (CPO, CEO, VP) in labels |
| 12c | Deprecations consolidation | Ensure all deprecation/sunset/migration notices appear exactly once as a single bundled bullet under Enterprise and Security Updates. Remove any standalone # Migration Notices section and remove duplicated deprecation links from other sections. |
| 12d | Root-cause guard scan | Flag legal/CCC content outside an active Enterprise/Security/Governance/Legal/Compliance heading path, 3+ VS Code version numbers in body prose, authenticated/private App release-process notes, and release-inventory-backed CLI/App bullets with too few inline capability links. |
What ships with it
1 file 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.
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.
- 2mo ago First seen · 123 lines · 76 tokens per session scan A 74ed25a84d6b
newsletter-polishing is a skill published in the GitHub repository briancl2/CustomerNewsletter (11 stars, last pushed 5mo ago), licensed MIT. It adds 76 tokens to every session and 2,172 once invoked, about $0.0003 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.
newsletter-polishing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| newsletter-polishingbriancl2/CustomerNewsletter | Skill | 11 | 5mo ago | MIT | A | 76 | Claude Code, Codex |
| trulens-diagnosistruera/trulens | Skill | 3.6k | yesterday | MIT | A | 17 | Claude Code, Codex |
| agents-sdk-dotnet-activityhandler-migrationmicrosoft/Agents | Skill | 1.1k | yesterday | MIT | A | 76 | Claude Code |
| agents-sdk-dotnetmicrosoft/Agents | Skill | 1.1k | yesterday | MIT | A | 112 | Claude Code |
| agents-sdk-typescript-otelmicrosoft/Agents | Skill | 1.1k | yesterday | MIT | A | 88 | Claude Code |
| bf-to-agents-sdk-dotnet-migrationmicrosoft/Agents | Skill | 1.1k | yesterday | MIT | A | 56 | Claude Code |
| github-review-prfeiskyer/claude-code-settings | Skill | 1.7k | yesterday | MIT | A | 90 | Claude Code |