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.
curl -O https://raw.githubusercontent.com/badsectorlabs/ludus-skills/main/.claude/commands/sync-ludus-docs.mdgit clone --depth 1 https://github.com/badsectorlabs/ludus-skillsWrote 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.
[](https://agentmods.dev/commands/badsectorlabs/ludus-skills/sync-ludus-docs)<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>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.
| Model | Per session | Once 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 |
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.
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)
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.
- 8d ago First seen · 165 lines · 37 tokens per session scan A f9d3b2cb9c48
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.