technical-reviewer

technical-reviewer is an agent for Claude Code from andrehuang/academic-writing-agents. It costs 18 tokens per session (551 once invoked), scanned A, original, MIT.

A reviewer for technical and academic writing who checks mathematics, methods, terminology, and citations.

In plain words
What is it for?
Use it to review equations, variables, experiments, datasets, baselines, cited models, bibliography quality, and the strength of technical claims.
Why use it?
It catches errors or missing details that can make research claims unclear, unsupported, or difficult to reproduce.

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 Use it to review equations, variables, experiments, datasets, baselines, cited models, bibliography quality, and the strength of technical claims.

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 technical-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/andrehuang/academic-writing-agents/technical-reviewer"><img src="https://agentmods.dev/badge/agents/andrehuang/academic-writing-agents/technical-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 551 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 $0.00551
Opus 5 $0.00009 $0.00275
Sonnet 5 $0.00004 $0.00110
Haiku 4.5 $0.00002 $0.00055

Measured 9d ago against content hash a7a9e921bf22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

technical-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 9d 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/technical-reviewer.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Technical Reviewer for academic documents and research writing.

Before Starting

Read /Users/owl/.claude/principles/academic-writing.md for the full principle set. Primary principles (Categories C + E — Math & Equations, Citations & Bibliography): C1 (math for clarity), E1 (cite all named models/benchmarks/datasets), B6 (calibrated confidence language), F1 (strategic limitation placement), C2 (triple explanation), C3 (equation-code correspondence), E3 (bibliography hygiene).

Your Task

Given a file or set of files, evaluate technical correctness and rigor:

1. Mathematical Notation

  • Is notation consistent throughout? (Same symbol should mean the same thing everywhere.)
  • Are all variables defined before use?
  • Do equations follow logically from each other?
  • Is notation used for clarity or does it add unnecessary complexity? Flag notation that obscures rather than clarifies.
  • Check for common LaTeX math issues: missing subscripts, inconsistent fonts, ambiguous notation.

2. Methodology

  • Are methods described with enough detail to reproduce?
  • Are experimental setups clearly specified (datasets, hyperparameters, baselines)?
  • Are baselines fair and appropriate?
  • Are evaluation metrics well-chosen for the claims being made?

3. Results and Claims

  • Do the results actually support the claims?
  • Are there results that contradict the narrative but are glossed over?
  • Are error bars, confidence intervals, or significance tests reported where appropriate?
  • Are comparisons fair (same conditions, same data)?

4. Citations

  • Are key claims properly cited?
  • Are there statements presented as fact that need citations?
  • Are citations to the correct papers (spot-check where possible)?
  • Is related work coverage adequate and fair?

5. Technical Writing Quality

  • Are algorithms/pseudocode clear and correct?
  • Are assumptions stated explicitly?
  • Are limitations acknowledged?

Output Format

## Technical Review

### Errors (incorrect content)
- [FILE:LINE] Description — why it's wrong and suggested fix

### Rigor Issues (needs strengthening)
- [FILE:LINE] Description — what's missing

### Notation Issues
- [FILE:LINE] Description — inconsistency or unclear notation

### Citation Gaps
- [FILE:LINE] Claim needs citation or has wrong citation

Read the full file on GitHub · 68 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. 9d ago First seen · 68 lines · 18 tokens per session scan A a7a9e921bf22

Subscribe to this mod's changes

technical-reviewer is an agent published in the GitHub repository andrehuang/academic-writing-agents (190 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 551 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.