vac

A command for checking whether Steam player accounts have Valve Anti-Cheat (VAC) or other platform bans. It accepts SteamID64 numbers or Steam profile names and reports the results for multiple players.

In plain words
What is it for?
Use it to screen player accounts, review VAC and game bans, check community or economy restrictions, and collect profile links.
Why use it?
It avoids checking each Steam account separately and puts ban details into one readable table.

Command for Claude Code

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 commands/stealthsrc/steam-mcp/vac
Clone the repo
git clone --depth 1 https://github.com/stealthsrc/steam-mcp

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 305 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 $0.00013 $0.00305
Opus 5 $0.00006 $0.00152
Sonnet 5 $0.00003 $0.00061
Haiku 4.5 $0.00001 $0.00030

Measured yesterday against content hash 16ac9f0e33f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vac 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 yesterday.

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/steam/vac.md · 35 lines

What it actually says

Check ban status for: $ARGUMENTS

The argument is one or more Steam identifiers separated by spaces (SteamID64 or vanity URLs). Examples:

  • stealthylabs
  • gabelogannewell robinwalker
  • player1 player2 player3

Steps:

  1. For any vanity URLs (non-numeric), use steam_get_player_summary to resolve names and SteamID64s
  2. Collect all SteamID64s, then call steam_get_player_bans with the full list in one request
  3. Call steam_get_player_summary for each ID to get display names (can batch if already resolved above)

Present the results as a clear table:

VAC / Ban Check

Player SteamID VAC Banned VAC Bans Game Bans Community Ban Economy Days Since Ban

Use clear indicators:

  • No bans: "Clean"
  • VAC banned: "VAC x{N}" with days since last ban
  • Game banned: "Game x{N}"
  • Community banned: "Community"

After the table, add Steam profile links for each player:

If any player has bans, add a note at the bottom summarizing the flagged accounts.

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. yesterday First seen · 35 lines · 13 tokens per session scan A 16ac9f0e33f9

Subscribe to this mod's changes

vac is a command published in the GitHub repository stealthsrc/steam-mcp (1 stars, last pushed 8d ago), licensed MIT. It adds 13 tokens to every session and 305 once invoked, about $0.0001 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.