prompt-check

prompt-check is a skill for Claude Code, Codex from Grinv/steam-games-mcp. It costs 54 tokens per session (666 once invoked), scanned A, original, MIT.

A testing procedure for checking every prompt exposed by an MCP server through the real MCP connection. It tests prompts with missing, optional, whitespace-only, and combined arguments to find handling errors.

In plain words
What is it for?
It is for testing new or changed MCP prompts, validating how their arguments are handled, and checking that the server's tools and prompts work through the live protocol.
Why use it?
It catches problems that reading the source code or checking only the prompt schema may miss, especially errors caused by particular argument combinations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is npx @modelcontextprotocol/inspector --cli node dist/index.js --method prompts/list.

Good fit It is for testing new or changed MCP prompts, validating how their arguments are handled, and checking that the server's tools and prompts work through the live protocol.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Grinv/steam-games-mcp
agentmods
npx agentmods add skills/grinv/steam-games-mcp/prompt-check

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for prompt-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/grinv/steam-games-mcp/prompt-check/github.svg)](https://agentmods.dev/skills/grinv/steam-games-mcp/prompt-check)
Your own site
<a href="https://agentmods.dev/skills/grinv/steam-games-mcp/prompt-check"><img src="https://agentmods.dev/badge/skills/grinv/steam-games-mcp/prompt-check/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prompt-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/grinv/steam-games-mcp/prompt-check"><img src="https://agentmods.dev/badge/skills/grinv/steam-games-mcp/prompt-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 666 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00054 $0.00666
Opus 5 $0.00027 $0.00333
Sonnet 5 $0.00011 $0.00133
Haiku 4.5 $0.00005 $0.00067

Measured 10d ago against content hash 2e0d9d21a58e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

prompt-check 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 10d 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.

.agents/skills/prompt-check/SKILL.md · 50 lines

What it actually says

Prompt check — live-test every MCP Prompt argument combination

A static read comparing prompt text against tool names/params misses argument-handling bugs. Actually render every prompt through the real MCP protocol:

npx @modelcontextprotocol/inspector --cli node dist/index.js --method prompts/list
npx @modelcontextprotocol/inspector --cli node dist/index.js --method prompts/get \
  --prompt-name <name> --prompt-args key=value key2=value2

--prompt-args takes space-separated key=value pairs, not a JSON blob — the CLI rejects JSON with "Invalid parameter format".

Run each prompt with no args, with only one of several optional args set at a time, and with all of them set — an argument that's individually optional can still have a bug that only shows up when given alone. Also try a whitespace-only value (" ") for every optional string arg, not just omitted-vs-present: it's truthy in JS, so a missing .trim() on prompts.ts's own argsSchema (separate from tools/*.ts's, and not automatically covered by a tool-schema trim fix like 61fe40a) slips past a field ? ... : .../field ?? "default" check the same way an actually-set value would.

Validate every tool call the rendered text instructs against that tool's actual inputSchema and documented caps — reading the prompt for plausible tool/param names isn't enough. Both live-confirmed here: deals_digest rendered min_discount values outside discover_games' own 1-100 range, and what_should_i_play told the agent to read ownership off get_owned_games' games list, which is capped at the top 50 by playtime and whose own source comment says it is not reliable for ownership (check_appids is).

Watch out for a SteamID64 argument specifically: the inspector CLI's own --prompt-args key=value parsing silently coerces a numeric-looking value through a JS number, and a 17-digit SteamID64 exceeds Number.MAX_SAFE_INTEGER — it comes out the other side with its last couple of digits corrupted (e.g. ...930...940), even though the prompt's own z.string() schema never asked for that. Confirmed this is the inspector's bug, not this server's, by sending the identical prompts/get call as raw JSON-RPC over stdio (a JSON string round-trips exactly) — don't spend time chasing this as a steam-games-mcp finding if it recurs; just verify any SteamID64-argument prompt test that way instead of trusting the inspector CLI's rendering of the digits.

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. 10d ago First seen · 50 lines · 54 tokens per session scan A 2e0d9d21a58e

Subscribe to this mod's changes

prompt-check is a skill published in the GitHub repository Grinv/steam-games-mcp (4 stars, last pushed 17d ago), licensed MIT. It adds 54 tokens to every session and 666 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

audit-prd

Audit a multi-section PRD with deterministic Hard Output Rules and cross-section consistency checks. Use when reviewing a complete product requirements document, checking FR-to-AC coverage, acceptance-criteria numbering, story-point arithmetic, or test traceability.

cdeust/ai-architect-mcp-spec · 51 tokens

api-testing

Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.

cyanheads/pubmed-mcp-server · 46 tokens

add-test

Scaffold a test file for an existing tool, resource, or service. Use when the user asks to add tests, improve coverage, or when a definition exists without a matching test file.

cyanheads/pubmed-mcp-server · 41 tokens

add-test

Use when adding unit or integration tests. Provides test patterns, naming conventions, and fixtures for Python (pytest), TypeScript (vitest), Java (JUnit/Mockito), and Rust.

open-metadata/ai-sdk · 40 tokens

run-integration

Use when running integration tests against a real Metadata instance. Guides setup of environment variables (AISDKHOST, AISDKTOKEN) and runs tests that make actual API calls.

open-metadata/ai-sdk · 40 tokens

lore-onboard

First-time setup wizard for LoreConvo. Verifies the MCP server is connected, the database is accessible, hooks are configured, and runs a test save/load cycle. Use when the user says "set up loreconvo", "onboard", "/lore-onboard", "verify loreconvo", "test loreconvo setup", or after first installing the plugin.

labyrinth-analytics/loreconvo · 81 tokens