agentmods.dev

TezAtlas: Command for Claude Code

.claude/commands/cross-review.md

cross-review is a command for Claude Code from tialkan/TezAtlas. It costs 0 tokens per session (465 once invoked), scanned A, original, MIT.

A command that sends a research draft to reviewers using models from companies other than the one writing it, then places their findings side by side. It checks project files and required access settings before running the review.

In plain words
What is it for?
Use it to review a draft, compare outside model feedback, inspect source-claim support, and decide which findings to address.
Why use it?
Independent reviews can expose issues the original writer or model overlooked, while prerequisite checks prevent a review from running with missing setup.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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 →

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/cross-review.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 cross-review

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/tialkan/tezatlas/cross-review"><img src="https://agentmods.dev/badge/commands/tialkan/tezatlas/cross-review.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 465 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 $0.00465
Opus 5.5 $0.00000 $0.00186
Sonnet 5.5 $0.00000 $0.00093
Haiku 4.5 $0.00000 $0.00047

Measured today against content hash 1ae54a3273a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cross-review 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/cross-review.md · 23 lines

What it actually says

You are TezAtlas. The user typed /cross-review $ARGUMENTS.

Goal: have the draft reviewed blind by models from other companies than the one writing it, put the findings side by side, and let the user decide. Full guide: docs/coklu-model.md.

Steps

  1. $ARGUMENTS is the draft path (e.g. bolumler/giris.md). If empty, ask which section to review, offering the most recently edited draft first.
  2. Check prerequisites without printing secrets:
    • .env exists and defines OPENROUTER_API_KEY (check with grep -c '^OPENROUTER_API_KEY=.\+' .env, never print the value). If missing, explain the one-time setup in docs/coklu-model.md and stop.
    • Note folder notes/ or notlar/ exists. If not, warn that source-claim checks will be weak and ask whether to continue.
    • The reviewers in agents.yaml (capraz_denetim) must not include an Anthropic model, because you (Claude) are the writer. If one does, tell the user and suggest replacing it.
  3. Run: 
    tezatlas-agents capraz_denetim --input "$ARGUMENTS"
    (or python3 agents/run.py capraz_denetim --input ... if the package is not installed). Report the cost line it prints.
  4. Open the report (<draft>_DENETIM.md). Walk the user through it, common findings first:
    • For each finding with alıntı taslakta: hayır, first check the draft yourself; say if the reviewer was wrong.
    • For source findings, open the cited note (and the PDF via /citation-check if needed) before agreeing.
    • Do not defend the draft just because you wrote it. Do not rewrite core arguments or conclusions; propose minimal fixes and let the user choose.
  5. Record the user's decision on each finding in the report's "Kararınız" lines.
  6. Remind the user that the report and decisions can support their AI-use disclosure if their institution requires one.
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 · 23 lines · 0 tokens per session scan A 1ae54a3273a3

Subscribe to this mod's changes

cross-review 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 465 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.

Code reviewResearch
Related

cross-review compared with commands from other repositories

cross-review next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cross-reviewtialkan/TezAtlasCommand3312d agoMITA0Claude Code
diff-reviewcoco-research/cocoCommand628yesterdayApache-2.0A11Claude Code
review-branchdamusix/atomic-claudeCommand1165d agoMITA35Claude Code
initazrtydxb/procoderCommand211yesterdayApache-2.0A16Claude Code
refactorRchGrav/claudeboxCommand1.2k1mo agoMITA9Claude Code
spec-trace-requirementsrjmurillo/ai-agentsCommand49todayMITA0GitHub Copilot
merge-conflict-analysisrjmurillo/ai-agentsCommand49todayMITA0GitHub Copilot