Borrowing it
Nothing to install: this file belongs to Grinv/mal-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Grinv/mal-mcp/main/.agents/skills/prompt-check/SKILL.mdgit clone --depth 1 https://github.com/Grinv/mal-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/skills/grinv/mal-mcp/prompt-check)<a href="https://agentmods.dev/skills/grinv/mal-mcp/prompt-check"><img src="https://agentmods.dev/badge/skills/grinv/mal-mcp/prompt-check.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 5.1 | $0.00053 | $0.00507 |
| Opus 5 | $0.00026 | $0.00253 |
| Sonnet 5 | $0.00011 | $0.00101 |
| Haiku 4.5 | $0.00005 | $0.00051 |
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 6d 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.
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".
For each of the three prompts, cover every combination of optional args, not just "all set" or "all omitted":
recommend_similar: notitle(should ask which anime, not fail — confirm the client actually gets asked rather than the call erroring),titleset to something real,titleset to something with no search results.seasonal_overview: neitherseasonnoryear, onlyseason, onlyyear, both together. Giving just one ofseason/yearalone renders identically to giving neither ("the current season," no args passed toget_seasonal_anime) — this is correct, not a bug:get_seasonal_anime's own description says supplying only one is treated as omitting both (matchesgetSeason()'sp.year && p.season ? ... : "seasons/now"insrc/clients/tenrai.ts), so the prompt mirrors the tool's own contract. Don't flag this from a source-only read of the prompt's branching alone — it resembles the "argument that's individually optional but breaks when given alone" bug class, but here the "breakage" is intended.hidden_gems: nokind,kind=anime,kind=manga— each is a genuinely different branch (different top-list tool).
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.
- 6d ago First seen · 39 lines · 53 tokens per session scan A b8e41e29545f
prompt-check is a skill published in the GitHub repository Grinv/mal-mcp (2 stars, last pushed 13d ago), licensed MIT. It adds 53 tokens to every session and 507 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.
Other skills, from other repositories
live-audit
Audit steam-games-mcp — build/test/lint gate, live MCP tool edge-case sweep (input validation, SteamID64/vanity/appid edge cases, key-gating), and source-level code review. Use when asked to test/audit the published or just-fixed steam-games-mcp package, hunt for bugs/edge cases, or repeat "the same kind of testing as…
prompt-check
Live-test every MCP Prompt in src/tools/prompts.ts through the real MCP protocol (not a static read) across every argument combination. Use when a prompt is added or its argument-handling logic changes, or as part of a live-audit pass.
tool-description-check
Self-check a new or edited MCP tool description/field .describe() text before committing — verify every behavioral claim against live testing or source, check for contradictions with sibling tools, and score against Glama's Tool Definition Quality Score (TDQS) rubric. Use whenever a tool description or schema field…
release
Cut a release of steam-games-mcp — draft CHANGELOG entries, check docs/metadata consistency, then bump/tag/push. Use when asked to release, cut a version, or publish a new version of this package.
docs-consistency-check
Check README/manifest.json/server.json/CHANGELOG.md/AGENTS.md and docs/.md for drift against the actual registered tools and source. Use after adding, renaming, or removing a tool, or as part of a live-audit pass.
verify-cli
Run smoke tests against the mpak CLI to verify all commands work correctly before publishing a new release.