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.
npx agentmods add commands/stealthsrc/steam-mcp/librarygit clone --depth 1 https://github.com/stealthsrc/steam-mcpWhat 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 | $0.00017 | $0.00314 |
| Opus 5 | $0.00009 | $0.00157 |
| Sonnet 5 | $0.00003 | $0.00063 |
| Haiku 4.5 | $0.00002 | $0.00031 |
Grade A, and why
library 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.
What it actually says
Analyse the Steam library for: $ARGUMENTS
Do the following in parallel:
steam_get_owned_gameswith limit=500, sort_by="playtime", include_appinfo=truesteam_get_recently_playedwith count=10
Then compute and present:
Library Analysis - {Player}
Overview:
- Total games owned: X
- Games never launched (backlog): Y (Z%)
- Games with > 100h: N
- Total hours tracked: H
Top 10 Most Played: | # | Game | AppID | Playtime | (with store links: https://store.steampowered.com/app/{appid}/)
Backlog highlights (owned but 0 minutes played - show up to 10 random ones): | Game | AppID | Store |
Gamer profile (AI-generated based on the data): Write 2-3 sentences describing the player's gaming habits based on the genres/games visible in their top played list. Example: "You seem to favour long-form open-world games and competitive shooters, with a strong investment in simulation titles."
Recent activity (last 2 weeks): (from steam_get_recently_played)
Links
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.
- yesterday First seen · 37 lines · 17 tokens per session scan A c10de41c0a7d
library is a command published in the GitHub repository stealthsrc/steam-mcp (1 stars, last pushed 8d ago), licensed MIT. It adds 17 tokens to every session and 314 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.
Other commands, from other repositories
quick-fix
Make a small, obvious fix directly on the current branch. No sprint, no PLAN, no stories.
begin
Start Day workflow — context sync, observer audit, standup, sprint plan.
build
Build workflow — contract setup, execute, polish, security gate, ship.
interrupt
Interrupt Protocol — snapshot current work and pivot to urgent task.
speckit.specify
Create or update the feature specification from a natural language feature description.
speckit.checklist
Generate a custom checklist for the current feature based on user requirements.