batch-review

batch-review is a command for coding agents from animalzinc/claude-plugins. It costs 9 tokens per session (1,765 once invoked), scanned A, original, MIT.

A batch content-review command that checks multiple Markdown articles against an existing editorial style guide. Markdown is a plain-text format commonly used for structured documents.

In plain words
What is it for?
Use it to review a directory of articles, preview changes with a dry run, or apply corrections automatically when configured.
Why use it?
It avoids reviewing articles one by one and can identify or apply style corrections across a folder.

Command

Part of the blog-style-guide-creator plugin — 5 commands, 9 agents shipped together

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 commands/animalzinc/claude-plugins/batch-review
Clone the repo
git clone --depth 1 https://github.com/animalzinc/claude-plugins

Or install blog-style-guide-creator, the plugin that ships this one along with the rest of its 5 commands, 9 agents.

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 batch-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/animalzinc/claude-plugins/batch-review.svg)](https://agentmods.dev/commands/animalzinc/claude-plugins/batch-review)
Your own site
<a href="https://agentmods.dev/commands/animalzinc/claude-plugins/batch-review"><img src="https://agentmods.dev/badge/commands/animalzinc/claude-plugins/batch-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,765 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 $0.00009 $0.01765
Opus 5 $0.00005 $0.00882
Sonnet 5 $0.00002 $0.00353
Haiku 4.5 $0.00001 $0.00177

Measured 5d ago against content hash 27c28f4bc71e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

batch-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 5d 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.

plugins/blog-style-guide-creator/commands/batch-review.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Batch Review: Process Multiple Articles

Review all articles in $2 against the $1 brand style guide.

Step 1: Validate Inputs

Before proceeding:

  • Verify style guide exists at brands/$1/style-guide.md
    • If missing: Error and suggest running /generate-style-guide $1 [source]
  • Verify directory exists at $2
    • If missing: Error with clear message
  • Check for --auto-apply flag (determines whether to apply corrections automatically)
  • Check for --dry-run flag (shows what would be changed without modifying files)
  • Note: --dry-run takes precedence over --auto-apply if both are specified

Step 2: Discover Articles

Scan the directory at $2 for markdown files:

  • Use Glob to find all *.md files in $2
  • Exclude files ending with _edited.md (already processed)
  • Exclude README.md files
  • Sort by filename
  • Report number of articles found

If no articles found:

  • Provide clear message and exit

If articles found:

  • Display list of articles to be reviewed
  • Ask user to confirm: "Found [X] articles. Proceed with batch review? (yes/no)"

Step 3: Process Each Article

For each article in the list:

Option A: Sequential Processing (Default - More Reliable)

  1. Display: "Processing article [N] of [total]: [filename]"
  2. Run the equivalent of /style-check $1 [article-path] on this article
  3. Collect findings
  4. Handle based on flags:
    • If --dry-run: Show preview of changes for this article, no modifications
    • If --auto-apply: Apply corrections and save to edited/ folder
    • If neither: Just report findings
  5. Move to next article

Option B: Parallel Processing (Faster but Resource-Intensive)

  • If user confirms they want parallel processing:
  • Batch articles into groups of 3
  • Process each group in parallel
  • Note: This will spawn 24 agents per batch (8 agents × 3 articles)

Step 4: Aggregate Portfolio Results

After all articles processed, create portfolio compliance report:

# Batch Review Report: $1

**Brand:** $1
**Source Directory:** $2
**Review Date:** [current date]
**Articles Reviewed:** [number]
**Auto-Apply:** [yes/no]

---

## Portfolio Compliance Summary

**Overall Statistics:**
- Total articles reviewed: [X]
- Fully compliant (0 violations): [X] articles ([%])
- Minor issues (1-5 violations): [X] articles ([%])
- Moderate issues (6-15 violations): [X] articles ([%])
- Major issues (16+ violations): [X] articles ([%])

**Total Violations Across Portfolio:**
- Voice & Tone: [X] violations
- Grammar & Usage: [X] violations
- Punctuation: [X] violations
- Formatting: [X] violations
- Technical Standards: [X] violations
- Content Patterns: [X] violations
- Industry Terms: [X] violations

**Average violations per article:** [number]

---

## Most Common Violations

1. [Most frequent issue]: [X] occurrences across [Y] articles
2. [Second most frequent]: [X] occurrences across [Y] articles
3. [Third most frequent]: [X] occurrences across [Y] articles
4. [etc.]

---

## Article-by-Article Summary

| Article | Total Violations | Status | Priority |
|---------|-----------------|--------|----------|
| [filename-1] | [X] | ✅/⚠️/❌ | High/Med/Low |
| [filename-2] | [X] | ✅/⚠️/❌ | High/Med/Low |
| [etc.] | [X] | ✅/⚠️/❌ | High/Med/Low |

**Legend:**
- ✅ Fully compliant (0 violations)
- ⚠️ Minor issues (1-5 violations)
- ❌ Needs attention (6+ violations)

---

## Priority Recommendations

### High Priority Articles (Review First)
[List articles with major brand voice/structural issues]

### Medium Priority Articles
[List articles with consistency/formatting issues]

### Low Priority Articles
[List articles with minor polish needed]

---

## Common Patterns to Address

**Voice & Tone Issues:**
[List common voice/tone violations seen across multiple articles]

**Grammar & Usage Issues:**
[List common grammar violations]

**Formatting Issues:**
[List common formatting violations]

[etc.]

---

## Next Steps

1. Review high-priority articles first
2. Consider updating style guide if new patterns emerge
3. For articles with 0 violations: Consider them as exemplars
4. For articles with many violations: May indicate style guide misalignment

**Files Generated:**
- Batch report: docs/logs/[date]_batch-review_$1.md
- Individual reports: docs/logs/[date]_style-check_$1_[article].md (for each article)
- Edited articles: $2/../edited/ (if --auto-apply used)

Read the full file on GitHub · 238 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. 5d ago First seen · 238 lines · 0 tokens per session scan A 27c28f4bc71e

Subscribe to this mod's changes

batch-review is a command published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 15d ago), licensed MIT. It adds 9 tokens to every session and 1,765 once invoked, about $0.0000 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.