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/editorial-review/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/editorial-review)<a href="https://agentmods.dev/skills/briancl2/customernewsletter/editorial-review"><img src="https://agentmods.dev/badge/skills/briancl2/customernewsletter/editorial-review/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/editorial-review"><img src="https://agentmods.dev/badge/skills/briancl2/customernewsletter/editorial-review.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 | $0.00063 | $0.01226 |
| Opus 5.5 | $0.00025 | $0.00490 |
| Sonnet 5.5 | $0.00013 | $0.00245 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
editorial-review 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editorial Review Loop
Apply human editorial corrections to a Phase 4 newsletter and produce an updated version.
Quick Start
- Read the corrections file at
workspace/YYYY-MM_editorial_corrections.md - Read the current newsletter at
output/YYYY-MM_month_newsletter.md - Read
reference/editorial-intelligence.mdfor calibrated rules - Apply each correction to the newsletter
- Update intelligence files with new patterns
- Validate the updated newsletter
- Capture learnings in LEARNINGS.md
Inputs
- Corrections File:
workspace/YYYY-MM_editorial_corrections.md(required) - Current Newsletter:
output/YYYY-MM_month_newsletter.md(required) - Editorial Intelligence:
reference/editorial-intelligence.md(context) - Source Intelligence:
reference/source-intelligence/meta-analysis.md(context)
Output
- Updated Newsletter:
output/YYYY-MM_month_newsletter.md(overwrite in place) - Updated Intelligence: Changes to
reference/editorial-intelligence.mdif corrections reveal new patterns - New Learnings: Appended to
LEARNINGS.md
Corrections File Format
The human writes corrections to workspace/YYYY-MM_editorial_corrections.md. The required structure, sections, and per-item table format are defined in the single authoritative spec: correction-format.md. Use that document as the source of truth for how to structure and label all corrections.
When running this skill, assume the corrections file strictly follows references/correction-format.md and treat any deviations as format errors to be surfaced back to the human editor.
- Item name, what to do with it (remove / compress / bundle)
Bundling Corrections
[Items that should be combined or separated] | Bundle | Items | Treatment |
Depth Corrections
[Items that need more or less detail]
- Item name: expand / compress, what detail to add/remove
Tone/Framing Corrections
[Narrative or framing changes needed]
## Core Workflow
### Step 1: Parse Corrections
Read the corrections file and categorize each correction:
| Type | Action |
|------|--------|
| **Theme correction** | Rewrite lead section with new theme |
| **Missing item** | Add item with source URL and appropriate detail |
| **Wrong item** | Remove, compress, or bundle as specified |
| **Bundling correction** | Combine items or split them per instructions |
| **Depth correction** | Expand or compress specific items |
| **Tone/framing** | Rewrite affected sections |
### Step 2: Apply Corrections to Newsletter
For each correction, modify the newsletter in place:
1. **Theme changes**: Replace the lead section title, framing paragraph, and reorganize lead items
2. **Additions**: Insert new items in the appropriate section, following the content-format-spec
3. **Removals**: Delete the item entirely or compress into a bundle
4. **Bundling**: Merge items into a single bullet with sub-items, or split a bundle into separate bullets
5. **Depth changes**: Expand with sub-bullets or compress to a single line
6. **Tone changes**: Rewrite the affected paragraph(s)
### Step 3: Validate Updated Newsletter
Run validation:
```bash
bash .github/skills/newsletter-validation/scripts/validate_newsletter.sh output/YYYY-MM_month_newsletter.md
Check:
- All corrections applied (count corrections vs changes made)
- Validation passes (0 errors)
- Line count in expected range (100-170 lines)
- No new forbidden patterns introduced
- All new items have source URLs
Step 4: Update Intelligence Files
If corrections reveal new editorial patterns, update:
reference/editorial-intelligence.md: Add new theme triggers, adjust selection weights, add expansion/compression rulesreference/source-intelligence/meta-analysis.md: Note new source gaps or patterns- Selection criteria: If the correction shows a weight was miscalibrated
Only update when the correction reveals a PATTERN, not a one-off preference.
What ships with it
2 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.
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 · 134 lines · 63 tokens per session scan A 74ab55533eeb
editorial-review is a skill published in the GitHub repository briancl2/CustomerNewsletter (11 stars, last pushed 5mo ago), licensed MIT. It adds 63 tokens to every session and 1,226 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.
editorial-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| editorial-reviewbriancl2/CustomerNewsletter | Skill | 11 | 5mo ago | MIT | A | 63 | 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 |