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 instructions/grinv/steam-games-mcp/agents-mdgit clone --depth 1 https://github.com/Grinv/steam-games-mcpWrote 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/instructions/grinv/steam-games-mcp/agents-md)<a href="https://agentmods.dev/instructions/grinv/steam-games-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/grinv/steam-games-mcp/agents-md.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 | $0.02519 | $0.02519 |
| Opus 5 | $0.01260 | $0.01260 |
| Sonnet 5 | $0.00504 | $0.00504 |
| Haiku 4.5 | $0.00252 | $0.00252 |
Grade A, and why
steam-games-mcp AGENTS.md 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 4d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Single source of truth for working on this repository — for any model or
agent. CLAUDE.md only references this file (@AGENTS.md); keep all shared
guidance here, not in CLAUDE.md. (For end-user/runtime docs, see README.md.)
Project shape
A TypeScript MCP server for Steam. Hybrid backend, mirroring the mal-mcp/tmdb-mcp
pattern: store/game reads go through the Steam Storefront API
(store.steampowered.com/api/*) which needs no key, while player data
(profiles, libraries, achievements, friends) uses the official Steam Web API
(api.steampowered.com) which needs a free key. Design rationale (why two
clients, the keyless caveat, why no SteamDB/price-history, API references,
template reuse) lives in docs/architecture.md.
src/
index.ts # bin entry — calls start()
server.ts # buildServer() + start(); registers everything
config.ts # env → validated Config (zod)
version.ts # VERSION/USER_AGENT, kept in sync with package.json by a test
format/ # raw Steam payloads → trimmed, agent-facing shapes: storefront.ts,
# web.ts + webAchievements.ts (official Web API: player data /
# achievement lists), store.ts (keyless store-service summarizers:
# GetItems/Query/wishlist/recommendations) over storeCard.ts (their
# shared StoreItem/tag/compat/card/filter toolkit), shared.ts (helpers).
# Each shaper has a co-located *.schemas.ts (schema-first: the shaper
# builds its return value via `schema.parse({...})`, see Conventions);
# storeCard.ts shares store.schemas.ts with store.ts
lib/ # GENERIC carcass: http, rateLimit, cache, concurrency, errors,
# logger, result
clients/ # storefront.ts (keyless store), web.ts (official Web API; key
# optional; builds storeService.ts, exposed via `.store` for
# tools/webStore.ts), storeService.ts (modern store-browse/
# query/wishlist-sorted card services)
tools/ # storefront.ts, webStore.ts (keyless-capable Web API tools),
# webPlayer.ts (key-gated player tools), webShared.ts (steamid
# schema, steamIdTool helper and requireKey, shared by the two),
# common.ts (shared param schemas, toCompatFilters + reply
# wrapper across storefront+web), guard.ts, prompts.ts (MCP
# Prompts)
__tests__/ # node:test (*.test.ts) + helpers.ts
scripts/ # build-tests.mjs, run-tests.mjs, sync-version.mjs (+ its
# sync-version.d.mts declaration) (generic), check-api.mjs
# (domain), preversion-check.mjs (CHANGELOG gate)
.agents/skills/ # reusable agent workflows for this repo (e.g. live-audit/) —
# plain Markdown with a YAML frontmatter name/description,
# not tied to any one tool's orchestration features. Same
# skill name/layout as this project's sibling MCP servers
# (tmdb-mcp, mal-mcp, anilist-mcp-server) — sync
# improvements both ways rather than letting them drift.
# `.claude/skills` is a symlink here (Codex CLI/Gemini CLI
# read `.agents/skills` directly, Claude Code the symlink)
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.
- 4d ago First seen · 169 lines · 2,519 tokens per session scan A 6aab44d4e6e7
steam-games-mcp AGENTS.md is an instructions file published in the GitHub repository Grinv/steam-games-mcp (4 stars, last pushed 11d ago), licensed MIT. It adds 2,519 tokens to every session, about $0.0126 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 instructions, from other repositories
tmdb-mcp AGENTS.md
Instructions for Grinv/tmdb-mcp, covering agents.md, project shape, commands, conventions and testing the live/published server.
mal-mcp AGENTS.md
Instructions for Grinv/mal-mcp, covering agents.md, project shape, commands, conventions and testing the live/published server.
local_faiss_mcp CLAUDE.md
Instructions for nonatofabio/local_faiss_mcp, covering claude.md, project overview, architecture, key design principles and development commands.
yt-media-info-mcp AGENTS.md
AGENTS.md instructions for bartivs/yt-media-info-mcp, covering yt-media-info mcp — agent guide, quick start, architecture, key files and conventions.
minio-mcp-server CLAUDE.md
Claude Code instructions for saeedshoh/minio-mcp-server, covering claude.md, what this is, setup & running, configuration and architecture.
tmdb-mcp CLAUDE.md
Instructions for Grinv/tmdb-mcp, a project described as: MCP server for The Movie Database (TMDB) with IMDb/Rotten Tomatoes/Metacritic ratings via OMDb.