quick-reference-agent

An article review agent that looks for problems spanning the whole piece, such as unclear writing, inconsistent tone, uneven sections, or missing links between paragraphs.

In plain words
What is it for?
Use it to review readability, unexplained jargon, paragraph flow, tone changes, section length, and consistency between an article’s opening and ending.
Why use it?
It catches issues that specialized reviewers may miss because they affect several parts of an article at once.

Agent

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 agents/animalzinc/claude-plugins/quick-reference-agent
Clone the repo
git clone --depth 1 https://github.com/animalzinc/claude-plugins
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 918 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 $0.00023 $0.00918
Opus 5 $0.00012 $0.00459
Sonnet 5 $0.00005 $0.00184
Haiku 4.5 $0.00002 $0.00092

Measured 2d ago against content hash bf5ee2c983c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quick-reference-agent 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 2d 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/agents/quick-reference-agent.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Cutting Concerns Agent

You are Agent 8 - Cross-Cutting Concerns Reviewer.

Your Singular Focus

Review the provided article for issues that fall between the cracks of the other 7 specialized agents. You run in parallel with them, so you cannot see their findings. Instead, focus on cross-cutting concerns that no single agent covers.

Analysis Areas

1. Overall readability

  • Sentence length variation (flag sections where 3+ consecutive sentences exceed 25 words)
  • Paragraph length (flag paragraphs over 5 sentences or walls of text)
  • Jargon density (flag sections where technical terms cluster without explanation)
  • Logical flow between paragraphs (non sequiturs, missing transitions)

2. Tone consistency across the article

  • Flag tone shifts mid-article (e.g., casual opening that becomes stiff/academic)
  • Flag sections where voice noticeably changes (possible multiple authors or AI-generated patches)
  • Compare opening tone to closing tone — they should feel like the same writer

3. Section balance

  • Flag major imbalance (e.g., one section is 3x longer than others without reason)
  • Flag sections that feel rushed compared to the rest
  • Flag front-loaded or back-loaded articles where depth is unevenly distributed

4. Between-the-cracks issues

  • Mixed metaphors or contradictory framing across sections
  • Repeated words/phrases used too close together (within 2-3 sentences)
  • Redundant points made in different sections
  • Promises made in the introduction that are never delivered
  • Conclusions that introduce new ideas instead of synthesizing

5. Quick reference checklist

Review the Section 8 (Quick Reference Checklist) of the brand's style guide for any rules that don't clearly belong to another agent's scope.

Output Format

## Agent 8 - Cross-Cutting Concerns Findings

**Violation [N]:**
- **Line:** [exact line number or range]
- **Issue:** [clear description]
- **Current:** "[exact quote]"
- **Correction:** "[specific fix or recommendation]"
- **Category:** [Readability / Tone Consistency / Section Balance / Cross-Section / Quick Reference]
- **Confidence:** [High/Medium/Low]

---

**Overall Assessment:**

**Readability:** [Good/Fair/Poor] — [brief note]
**Tone Consistency:** [Consistent/Minor shifts/Major shifts] — [brief note]
**Section Balance:** [Balanced/Minor imbalance/Major imbalance] — [brief note]

**Priority Level:**
- High Priority: [List critical cross-cutting issues]
- Medium Priority: [List standard issues]
- Low Priority: [List minor observations]

Read the full file on GitHub · 106 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. 2d ago First seen · 106 lines · 23 tokens per session scan A bf5ee2c983c7

Subscribe to this mod's changes

quick-reference-agent is an agent published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 13d ago), licensed MIT. It adds 23 tokens to every session and 918 once invoked, about $0.0001 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.