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/apigit 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 | $0.00018 | $0.00367 |
| Opus 5 | $0.00009 | $0.00183 |
| Sonnet 5 | $0.00004 | $0.00073 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
api 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
Register the steam-mcp MCP server using the provided key: $ARGUMENTS
Step 1 — Validate the argument
Check if $ARGUMENTS is empty, blank, or literally "YOUR_KEY".
If so, display this message exactly (do not paraphrase):
No API key provided.
Get your free Steam API key at:
https://steamcommunity.com/dev/apikey
Then run:
/steam:api YOUR_KEY
Example (this is what a real key looks like):
/steam:api A1B2C3D4E5F67890A1B2C3D4E5F67890
Stop here. Do not continue.
Step 2 — Detect the project path
Use the Bash tool to run pwd and capture the output as PROJECT_DIR.
The node entry point is: <PROJECT_DIR>/dist/index.js
On Windows, convert backslashes to forward slashes if needed.
Step 3 — Register the MCP server
Use the Bash tool to run:
claude mcp add steam-mcp -e STEAM_API_KEY=$ARGUMENTS -- node "<PROJECT_DIR>/dist/index.js"
- If the command succeeds: tell the user
steam-mcp registered. Restart Claude Code to activate the /steam:* commands. - If it fails with "already exists": run
claude mcp remove steam-mcpthen retry the add command, then report success. - If it fails for any other reason: show the raw error so the user can diagnose it.
Do NOT show the API key back to the user in any output.
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 · 49 lines · 0 tokens per session scan A 3aafa9c2579e
api is a command published in the GitHub repository stealthsrc/steam-mcp (1 stars, last pushed 8d ago), licensed MIT. It adds 18 tokens to every session and 367 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
deslop
Remove AI-generated code slop from the current branch's changes.
triage
Triage Linear issue with comprehensive analysis.
release
Perform a full release: generate release notes, bump version, commit, tag, and push.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.
migrate
Command "migrate" from chohra-med/expo_boilerplate, covering invocation, steps and rule.
audit
Command "audit" from chohra-med/expo_boilerplate, covering invocation, checks and output.