agentmods.dev

academic-writing-logic-reviewer

academic-writing-logic-reviewer is an agent for Claude Code from larsboes/Axon. It costs 51 tokens per session (312 once invoked), scanned A, original, MIT.

An academic argument checker for theses and research papers. It examines how ideas connect across paragraphs and sections, separate from sentence-level writing quality.

In plain words
What is it for?
Use it after drafting a thesis chapter, paper section, or other academic argument. It checks whether the progression from problem to approach, result, and implication makes sense.
Why use it?
It helps find logical jumps, repeated points, weak transitions, and a story that loses its direction. It reports problems without rewriting the text.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths.

Part of the writing plugin — 5 skills, 8 agents shipped together

not rated 1repo 1mo ago A scan 51 tokens original MIT

Good fit Use it after drafting a thesis chapter, paper section, or other academic argument. It checks whether the progression from problem to approach, result, and implication makes sense.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/larsboes/axon/academic-writing-logic-reviewer
View source ↗ larsboes/Axon larsboes.github.io
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.

Clone the repo
git clone --depth 1 https://github.com/larsboes/Axon

Made for: Claude Code.

Or install writing, the plugin that ships this one along with the rest of its 5 skills, 8 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 academic-writing-logic-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/larsboes/axon/academic-writing-logic-reviewer"><img src="https://agentmods.dev/badge/agents/larsboes/axon/academic-writing-logic-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 312 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 $0.00051 $0.00312
Opus 5.5 $0.00020 $0.00125
Sonnet 5.5 $0.00010 $0.00062
Haiku 4.5 $0.00005 $0.00031

Measured 2mo ago against content hash 520dbc43c828, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

academic-writing-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 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.

Packs/writing/agents/academic-writing-logic-reviewer.md · 27 lines

What it actually says

You review argument structure in academic writing (thesis chapters, papers), independent of whether individual sentences are well-written — that is a different reviewer's job. You do not edit — you report findings only.

For the target section, check:

  1. Does each part follow from what came before, or is there an unstated logical leap?
  2. Are paragraph-to-paragraph transitions doing real argumentative work, or just juxtaposing adjacent facts?
  3. Is anything redundant — the same point made twice without new evidence the second time?
  4. Does the narrative arc (problem → approach → result → implication) hold across the whole section, or does it wander?

For flow diagnostics specifically (reverse-outlining, transition-word audit, given-new sentence flow — a different, complementary check from argument-structure review), read ~/.claude/skills/academic-writing/references/flow-diagnostics.md and apply it if asked for a flow pass rather than a pure logic pass.

Report each finding as: location → the specific logical gap or redundancy → what's missing to close it. If the argument genuinely holds together, say so explicitly rather than inventing a gap.

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. 2mo ago First seen · 27 lines · 51 tokens per session scan A 520dbc43c828

Subscribe to this mod's changes

academic-writing-logic-reviewer is an agent published in the GitHub repository larsboes/Axon (1 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 312 once invoked, about $0.0002 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 2026-08-31.

ResearchWriting and docsagent-skillsai-agentsbazelclaudeintegration-platformlocal-first
Related

academic-writing-logic-reviewer compared with agents from other repositories

academic-writing-logic-reviewer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
academic-writing-logic-reviewerlarsboes/AxonAgent11mo agoMITA51Claude Code
tauri-security-reviewerkevinlin/cowork-zAgent137d agoMITA91Claude Code
ipc-contract-auditorkevinlin/cowork-zAgent137d agoMITA105Claude Code
sverklo-exploresverklo/sverkloAgent822mo agoMITA96Claude Code
orbit-code-editordanieljhkim/orbitAgent102mo agoMITA63Claude Code
bank-extractledq/resumeryAgent21mo agoMITA91Claude Code
orbit-task-pilotdanieljhkim/orbitAgent102mo agoMITA34Claude Code