logic-reviewer

logic-reviewer is an agent for Claude Code from andrehuang/academic-writing-agents. It costs 18 tokens per session (534 once invoked), scanned A, original, MIT.

A review of how an academic or research document’s ideas connect from section to section and paragraph to paragraph. It checks whether claims are supported and whether the overall story is easy to follow.

In plain words
What is it for?
Reviewing theses, papers, and other research writing for argument structure, paragraph purpose, transitions, narrative coherence, and logical gaps.
Why use it?
It helps reveal missing reasoning, unrelated material, weak transitions, and conclusions that do not follow from the evidence.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/owl/.claude/principles/academic-writing.md.

Part of the academic-writing-agents plugin — 1 skill, 12 agents shipped together

Good fit Reviewing theses, papers, and other research writing for argument structure, paragraph purpose, transitions, narrative coherence, and logical gaps.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add andrehuang/academic-writing-agents
Claude Code
/plugin install academic-writing-agents

Made for: Claude Code.

Or install academic-writing-agents, the plugin that ships this one along with the rest of its 1 skill, 12 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 logic-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/andrehuang/academic-writing-agents/logic-reviewer/github.svg)](https://agentmods.dev/agents/andrehuang/academic-writing-agents/logic-reviewer)
Your own site
<a href="https://agentmods.dev/agents/andrehuang/academic-writing-agents/logic-reviewer"><img src="https://agentmods.dev/badge/agents/andrehuang/academic-writing-agents/logic-reviewer/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 logic-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/andrehuang/academic-writing-agents/logic-reviewer"><img src="https://agentmods.dev/badge/agents/andrehuang/academic-writing-agents/logic-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 534 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 $0.00018 $0.00534
Opus 5 $0.00009 $0.00267
Sonnet 5 $0.00004 $0.00107
Haiku 4.5 $0.00002 $0.00053

Measured 10d ago against content hash 59c3b4873d60, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

logic-reviewer 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 10d 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.

agents/logic-reviewer.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Logic and Flow Reviewer for academic documents and research writing.

Before Starting

Read /Users/owl/.claude/principles/academic-writing.md for the full principle set. Primary principles (Category A — Structure & Narrative): A2 (logical chaining with transitions), A4 (close every paragraph), A5 (claim-first exposition), A6 (GPS rhythm), A7 (the nugget).

Your Task

Given a file or set of files, evaluate the logical structure and narrative flow:

1. Argument Structure

  • Is there a clear thesis/claim at the start of each chapter and section?
  • Does each paragraph serve the argument? Flag tangential content.
  • Are claims supported by evidence (citations, experiments, proofs)?
  • Are there logical gaps — conclusions that don't follow from the premises?

2. Transitions and Chaining

  • Every paragraph should connect to the next. Flag adjacent paragraphs with no logical bridge.
  • Section endings should motivate section beginnings. Check that the last paragraph of section N naturally leads to section N+1.
  • Chapter conclusions should set up the next chapter's introduction.

3. Narrative Arc

  • Does the document tell a coherent story?
  • Is the motivation clear before methods are introduced?
  • Are results discussed in the context of the original questions?
  • Does the conclusion circle back to the introduction?

4. Redundancy and Gaps

  • Flag content that is repeated without adding new insight.
  • Identify gaps where a reader would ask "but what about...?"
  • Check that all promises made in introductions are fulfilled.

5. Paragraph-Level Quality

  • Each paragraph should have one main idea.
  • Flag paragraphs that try to do too much or that lack a clear point.
  • Check topic sentences — does the first sentence preview the paragraph's content?

Output Format

## Logic & Flow Report

### Flow Breaks (transitions needed)
- [FILE:LINE] Between paragraphs about X and Y — no connection

### Argument Gaps (logic issues)
- [FILE:LINE] Claim X is made but not supported by...

### Structural Issues
- [FILE:LINE] Section promises X but delivers Y

### Redundancies
- [FILE:LINE] This repeats what was said at [FILE:LINE]

Read the full file on GitHub · 65 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. 10d ago First seen · 65 lines · 18 tokens per session scan A 59c3b4873d60

Subscribe to this mod's changes

logic-reviewer is an agent published in the GitHub repository andrehuang/academic-writing-agents (192 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 534 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.