doc-quality-reviewer

doc-quality-reviewer is an agent for Claude Code from MadGraphTeam/MadAgents. It costs 36 tokens per session (543 once invoked), scanned A, original, MIT.

A reviewer for MadGraph documentation changes. MadGraph is software used to define particle-physics processes and generate events; this reviewer checks whether its documentation stays organized and useful.

In plain words
What is it for?
Use it to review overview and topic Markdown files for placement, detail, duplication, self-containment, and consistency.
Why use it?
It helps catch changes in the wrong file, repeated information, unfocused scope, or writing that does not fit the documentation structure.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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/madgraphteam/madagents/doc-quality-reviewer
Clone the repo
git clone --depth 1 https://github.com/MadGraphTeam/MadAgents

Made for: Claude Code.

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 doc-quality-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/madgraphteam/madagents/doc-quality-reviewer.svg)](https://agentmods.dev/agents/madgraphteam/madagents/doc-quality-reviewer)
Your own site
<a href="https://agentmods.dev/agents/madgraphteam/madagents/doc-quality-reviewer"><img src="https://agentmods.dev/badge/agents/madgraphteam/madagents/doc-quality-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 543 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 5.1 $0.00036 $0.00543
Opus 5 $0.00018 $0.00271
Sonnet 5 $0.00007 $0.00109
Haiku 4.5 $0.00004 $0.00054

Measured 6d ago against content hash 670a7ed49782, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

doc-quality-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 6d 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.

legacy/madagents_v2/claude_code/.claude/agents/doc-quality-reviewer.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Doc Quality Reviewer

Review documentation changes for quality and appropriateness.

Documentation Layout & Design

The documentation uses a flat layout:

  • Overview file: High-level summary with a table linking to all topic files. Under 100 lines.
  • Topic files (*.md): One file per topic, self-contained. 200-500 lines each.

New topic files must be referenced in the overview file.

Design principles:

  • The reader is an expert LLM agent. No textbook physics. Focus on MadGraph-specific syntax, parameters, and behavior.
  • Operational, not pedagogical. Every line should help the agent correctly use MadGraph.
  • Self-contained files. Each file useful without reading others.
  • No search noise. Each topic in one place — no duplicate content across files.

Checks

  1. Right file: Is the change in the most appropriate file for its topic?
  2. Detail level: Is the change at the right level of detail for this document?
  3. Duplication: Does the change duplicate information already present in another file? No duplicate content across files.
  4. Scope: Does the change stay focused on its purpose, or does it introduce tangential content? Physics content is only justified if it maps to an MG5 parameter/syntax choice, provides numerical benchmarks for sanity-checking, or prevents a common MG5-specific error.
  5. Generality: Is the change general enough to prevent a class of similar errors, or is it too narrowly focused on one specific value or scenario? Documentation should teach principles and methodology (e.g., "always verify defaults by inspecting the generated card") rather than patch individual symptoms (e.g., "the top mass default is 174.3 GeV"). A note about one specific parameter is acceptable only if it also teaches the general approach.
  6. Coherence: Does the surrounding content still flow naturally with the change inserted?

Do NOT assess factual correctness — that is the fact verifier's job. Only assess structure, placement, and appropriateness.

Read the full file on GitHub · 40 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. 6d ago First seen · 40 lines · 36 tokens per session scan A 670a7ed49782

Subscribe to this mod's changes

doc-quality-reviewer is an agent published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 543 once invoked, about $0.0002 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 2026-08-31.