agentmods.dev

TezAtlas: Command for Claude Code

.claude/commands/review-draft.md

review-draft is a command for Claude Code from tialkan/TezAtlas. It costs 0 tokens per session (1,284 once invoked), scanned A, original, MIT.

A draft-review command for checking an academic section or manuscript. It reviews the argument, verifies links to sources, checks writing style, and can generate citation data from a file.

In plain words
What is it for?
Use it to review a file or pasted text, run language-specific style checks, inspect citations, and report issues in the draft.
Why use it?
It brings several review steps together and can reveal missing citations or style problems before a draft is submitted.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is tialkan/TezAtlas's own configuration. It tells Claude Code how to work on TezAtlas itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything TezAtlas configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 tools/bibtex_generator.py <file_path> --format bibtex.

not rated 33repo 12d ago A scan 0 tokens original MIT
View source ↗ tialkan/TezAtlas
Reuse

Borrowing it

Nothing to install: this file belongs to tialkan/TezAtlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tialkan/TezAtlas/main/.claude/commands/review-draft.md
Clone the repo
git clone --depth 1 https://github.com/tialkan/TezAtlas

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 review-draft

README.md
[![agentmods](https://agentmods.dev/badge/commands/tialkan/tezatlas/review-draft/github.svg)](https://agentmods.dev/commands/tialkan/tezatlas/review-draft)
Your own site
<a href="https://agentmods.dev/commands/tialkan/tezatlas/review-draft"><img src="https://agentmods.dev/badge/commands/tialkan/tezatlas/review-draft/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 review-draft

Your own site · 80×15
<a href="https://agentmods.dev/commands/tialkan/tezatlas/review-draft"><img src="https://agentmods.dev/badge/commands/tialkan/tezatlas/review-draft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,284 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 $0.00000 $0.01284
Opus 5.5 $0.00000 $0.00514
Sonnet 5.5 $0.00000 $0.00257
Haiku 4.5 $0.00000 $0.00128

Measured today against content hash 0b68e48fcbfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-draft 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 today.

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.

.claude/commands/review-draft.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are TezAtlas in Draft Review mode. The user has typed /review-draft.

This command performs a structured quality review of a draft section or manuscript. It combines argument integrity, source anchoring, and style linting into a single pass.

What to Do

  1. Identify the draft to review:

    • If the user provides a file path or text after /review-draft, use that.
    • Otherwise ask: "Hangi dosyayı veya bölümü gözden geçirelim? (Dosya yolunu ver veya metni yapıştır)"

  2. Read project context (if STATUS.md exists):

    • Read STATUS.md → get document_type, language, research_field.
    • Read ARGUMENTS.md → get declared arguments to cross-check.

  3. Generate citations for the draft (if a file path was given — runs before review):

    python3 tools/bibtex_generator.py <file_path> --format bibtex

    If the file contains PDFs in sources/ that are cited without BibTeX entries, offer to generate them. Show results as a numbered list of found/missing citations.

  4. Run the style linter (if a file path was given):

    python3 tools/style_linter.py <file_path> --lang <tr|en> --json

    Parse and display the JSON output.

  5. Display the review in three layers:

╔══════════════════════════════════════════════════════════════╗
║  TezAtlas — Taslak İnceleme / Draft Review                   ║
╠══════════════════════════════════════════════════════════════╣
║  Dosya: [FILE]    Dil: [LANG]    Alan: [FIELD]               ║
╚══════════════════════════════════════════════════════════════╝

Katman 1 — Argüman Bütünlüğü / Argument Integrity

For each paragraph/section:

  • Does every claim have a citation?
  • Does the paragraph advance one of the declared arguments in ARGUMENTS.md?
  • Flag any unsupported claims with: ⚠️ [KAYNAK GEREKLİ] — "..." iddiası kaynak belirtmiyor

Katman 2 — Kaynak Sağlamlığı / Source Integrity (Iron Rules 1 & 4)

  • Are cited sources present in sources/?
  • Flag any citation that looks fabricated or cannot be verified: 🚫 [DOĞRULAMA GEREKLİ] — "[Atıf]" kaynağı sources/ dizininde bulunamadı
  • Suggest running Citation Verifier for flagged claims: 
    python3 agents/run.py citation_verifier --claim "<claim>" --source sources/<file.pdf>

Read the full file on GitHub · 107 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. today First seen · 107 lines · 0 tokens per session scan A 0b68e48fcbfa

Subscribe to this mod's changes

review-draft is a command published in the GitHub repository tialkan/TezAtlas (33 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,284 tokens. 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 2026-11-07.

ResearchWriting and docs
Related

review-draft compared with commands from other repositories

review-draft next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
review-drafttialkan/TezAtlasCommand3312d agoMITA0Claude Code
checklistgithub/spec-kitCommand148ktodayMITA13Claude Code
clarifygithub/spec-kitCommand148ktodayMITA27Claude Code
specifygithub/spec-kitCommand148ktodayMITA13Claude Code
convergegithub/spec-kitCommand148ktodayMITA35Claude Code
speckit.bug.testgithub/spec-kitCommand148ktodayMITA13Claude Code
analyzegithub/spec-kitCommand148ktodayMITA26Claude Code