ludus-skills: Command for Claude Code

.claude/commands/sync-ludus-docs.md

sync-ludus-docs is a command for Claude Code from badsectorlabs/ludus-skills. It costs 37 tokens per session (2,775 once invoked), scanned A, original, MIT.

A command for comparing repository reference documents with the official Ludus documentation, which describes the Ludus cyber-range platform, and applying content-only updates.

In plain words
What is it for?
Use it to update reference files for Ludus skills, with evidence gathered in parallel and the final wording written by the main agent.
Why use it?
It helps keep local skill documentation aligned with upstream information while preserving the existing document structure.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is badsectorlabs/ludus-skills's own configuration. It tells Claude Code how to work on ludus-skills 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 ludus-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to badsectorlabs/ludus-skills. 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/badsectorlabs/ludus-skills/main/.claude/commands/sync-ludus-docs.md
Clone the repo
git clone --depth 1 https://github.com/badsectorlabs/ludus-skills

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 sync-ludus-docs

README.md
[![agentmods](https://agentmods.dev/badge/commands/badsectorlabs/ludus-skills/sync-ludus-docs.svg)](https://agentmods.dev/commands/badsectorlabs/ludus-skills/sync-ludus-docs)
Your own site
<a href="https://agentmods.dev/commands/badsectorlabs/ludus-skills/sync-ludus-docs"><img src="https://agentmods.dev/badge/commands/badsectorlabs/ludus-skills/sync-ludus-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,775 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 $0.00037 $0.02775
Opus 5 $0.00018 $0.01388
Sonnet 5 $0.00007 $0.00555
Haiku 4.5 $0.00004 $0.00278

Measured 8d ago against content hash f9d3b2cb9c48, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sync-ludus-docs 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 8d 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.

.claude/commands/sync-ludus-docs.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sync Ludus Skills With Upstream Docs

You are bringing this repository's skill reference files up to date with the official Ludus documentation at https://docs.ludus.cloud. The work is parallelized with subagents — one per skill — but subagents only gather evidence. They do not propose edit wording, they do not rate their own confidence, and they do not draft new content. The main agent is the only thing that composes text that ends up in a file, and it must always have seen the upstream page firsthand before doing so.

Why this shape

An earlier version of this command let subagents propose finished edits with self-rated confidence. It produced: a hallucinated schema field (primary_dns_server) marked HIGH confidence, a "missing flag" report for a flag that was already present in the file, and "not found upstream" claims that were actually "I didn't look at the right page." Every one of those failures had the same root cause: delegated judgment without delegated evidence. This version fixes that by making subagents return only verifiable pointers and forcing the main agent to re-fetch before writing.

Ground rules

  • Preserve structure. No reorganization, no heading renames, no reordering, no new top-level sections, no new files. Only factual content changes: command names, flag names, field names, enumerated values, error messages, environment lists, default values, version-specific behavior, links.
  • Upstream is source of truth. If the local reference disagrees with docs.ludus.cloud, the local reference is wrong — unless the upstream page contradicts the rest of the site (e.g., stale page still showing an old CLI shape).
  • No speculative edits. Every applied change must have a verbatim upstream quote in the main agent's own context window at the moment of the edit. If you don't have the source text in front of you, re-fetch before editing.
  • Do not commit. Stop after applying edits and summarize. The user reviews and commits.

Step 1 — Inventory (main agent, no subagents, no web fetches)

Read the full file on GitHub · 165 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. 8d ago First seen · 165 lines · 37 tokens per session scan A f9d3b2cb9c48

Subscribe to this mod's changes

sync-ludus-docs is a command published in the GitHub repository badsectorlabs/ludus-skills (9 stars, last pushed 28d ago), licensed MIT. It adds 37 tokens to every session and 2,775 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.