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.
git clone --depth 1 https://github.com/nitinjain999/platform-skillsnpx agentmods add commands/nitinjain999/platform-skills/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/commands/nitinjain999/platform-skills/mcp)<a href="https://agentmods.dev/commands/nitinjain999/platform-skills/mcp"><img src="https://agentmods.dev/badge/commands/nitinjain999/platform-skills/mcp/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.
<a href="https://agentmods.dev/commands/nitinjain999/platform-skills/mcp"><img src="https://agentmods.dev/badge/commands/nitinjain999/platform-skills/mcp.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00033 | $0.03362 |
| Opus 5 | $0.00016 | $0.01681 |
| Sonnet 5 | $0.00007 | $0.00672 |
| Haiku 4.5 | $0.00003 | $0.00336 |
Grade B, and why
mcp scanned grade B with 1 finding 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 9d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Claude Code (`~/.claude/settings.json` → `mcpServers`):** How it starts
The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build, review, or debug an MCP (Model Context Protocol) server or client.
Mode: create
Scaffold a production-ready MCP server.
Steps:
- Ask for: language (TypeScript or Python), transport (stdio / HTTP+SSE), list of tools and resources needed
- Generate project scaffold with correct SDK setup
- Implement tool handlers with Zod (TypeScript) or Pydantic (Python) schema validation
- Add resource providers and prompt templates as needed
- Configure transport layer
- Add error handling — return
isError: truecontent, never throw unhandled exceptions to clients - Add authentication and rate limiting for HTTP transports
- Provide MCP Inspector test commands and expected responses
- Add deployment checklist (env vars, secrets, logging)
Validation:
# Smoke-test the MCP server before connecting a host
npx @modelcontextprotocol/inspector <your-server-command>
# This opens an interactive inspector — verify: tools list, resources list, no startup errors
# If the server is not discovered by the host, run /platform-skills:mcp debug
Reference: references/mcp.md → Protocol Fundamentals, TypeScript SDK, Python SDK
Mode: review
Review an existing MCP server or client implementation.
Evaluate in priority order:
- Protocol compliance — JSON-RPC 2.0 correctness, proper capability negotiation, well-formed content arrays
- Schema validation — all tool inputs validated with Zod/Pydantic; no
z.any()or empty schemas - Security — no credentials in tool responses or resource content; auth on HTTP transports; rate limiting present
- Error handling — errors return
isError: truewith a message, not unhandled exceptions - Transport — correct transport for the use case; no blocking sync code in async transports
Output: Critical (must fix) / Improvement (should fix) / Note (informational)
Reference: references/mcp.md → Security, Error Handling, Testing and Debugging
Mode: debug
Diagnose MCP protocol or integration failures.
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.
- 9d ago First seen · 354 lines · 33 tokens per session scan B a134d246f52d
mcp is a command published in the GitHub repository nitinjain999/platform-skills (41 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 3,362 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
apollo-migrate
Migrate the Apollo repository $ARGUMENTS to the new GraphQLClientProtocol pattern.
f5-design
Generate design documents and specifications (D1-D4).
f5-backend
Backend development commands.
agent-backend-specialist
Dispatch hub:backend-specialist — Expert backend architect for Node.
better-auth:add-plugin
Add a better-auth plugin to an existing project. Configures server and client plugins with proper imports.
cloudflare-r2:presigned-url
Generate presigned URLs for secure client-side uploads or downloads.