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 skills/myeolinmalchi/mcp2cli/mcp-codegennpx skills add myeolinmalchi/mcp2cli --skill mcp-codegengit clone --depth 1 https://github.com/myeolinmalchi/mcp2cliWhat 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 | $0.00073 | $0.00472 |
| Opus 5 | $0.00036 | $0.00236 |
| Sonnet 5 | $0.00015 | $0.00094 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
mcp-codegen 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 2d 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
CLI Code Generation
Generate a TypeScript/npm-based CLI tool from an analyzed MCP server.
Prerequisites
Run mcp-analyze first to get the tool list, parameters, and pattern classification.
Step 1: Design CLI Command Structure
Map MCP tools to CLI commands:
Naming Convention:
- Tool prefix groups become subcommands:
lol_get_summoner_profile→<cli> lol profile - Single-domain tools become direct commands:
parse_document→<cli> parse - Use kebab-case for multi-word commands
Parameter Mapping:
- Required MCP params → positional CLI args
- Optional MCP params → named flags (
--flag value) - Boolean params → boolean flags (
--verbose,--no-cache) - Complex objects → JSON string flags or
--filereferences
Output Design:
- Default: human-readable formatted text
--json: raw JSON output for piping- Progress/status → stderr, data → stdout
Standard Flags (always include):
--help,--version,--json,--verbose/-v
Step 2: Generate Code
Always generate TypeScript/npm-based CLI tools, regardless of the source MCP server's language.
See references/cli-scaffold.md for the project template, stack, and implementation rules.
Select the appropriate code template from references/tier-1-templates.md or references/tier-2-templates.md based on the pattern classification from mcp-analyze.
If the pattern is Tier 3, see references/tier-3-strategies.md for partial conversion approach.
If the source MCP server is Python, see references/porting-cheatsheet.md for Python → TypeScript translation patterns (httpx → fetch, pydantic → interfaces, asyncio → ESM await, etc.).
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 48 lines · 73 tokens per session scan A d5479a0c46d6
mcp-codegen is a skill published in the GitHub repository myeolinmalchi/mcp2cli (4 stars, last pushed 5mo ago), licensed MIT. It adds 73 tokens to every session and 472 once invoked, about $0.0004 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
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…