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.
git clone --depth 1 https://github.com/runnithan/claudex-setupWrote 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/runnithan/claudex-setup/cli-tools-over-mcp-for-tokens)<a href="https://agentmods.dev/commands/runnithan/claudex-setup/cli-tools-over-mcp-for-tokens"><img src="https://agentmods.dev/badge/commands/runnithan/claudex-setup/cli-tools-over-mcp-for-tokens/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/runnithan/claudex-setup/cli-tools-over-mcp-for-tokens"><img src="https://agentmods.dev/badge/commands/runnithan/claudex-setup/cli-tools-over-mcp-for-tokens.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 | $0.00000 | $0.00395 |
| Opus 5 | $0.00000 | $0.00198 |
| Sonnet 5 | $0.00000 | $0.00079 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
cli-tools-over-mcp-for-tokens 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 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.
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
When an Agent Hits Friction, Build a CLI Tool: Not an MCP
TL;DR
Prefer giving agents small CLI tools over MCPs: a CLI is read once then driven by command, is deterministic, self-documents via --help, and costs far less context than an MCP's loaded tool schemas.
Why it matters
MCPs load tool schemas into context and negotiate opaquely; a CLI Claude can discover via --help/subcommands, drive predictably, and reuse across projects for a fraction of the tokens. This is the core move of harness/agentic engineering: remove a friction point by building a tool for it rather than doing it by hand or bolting on a heavy server. It complements mcp-servers-as-usb-ports-choose-selectively, still choose MCPs selectively, but reach for a CLI first when you control the integration.
How to apply
At each manual or agent-blocked step, write a small CLI (Python/Node/Go) that exposes the action with semantic subcommands and a real --help, put it on PATH, and reference it in a skill or CLAUDE.md so Claude discovers it. Keep outputs predictable and machine-readable. Reuse the same CLIs across projects; over time your friction points become a personal tool belt the agent drives itself.
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 · 26 lines · 0 tokens per session scan A 6bf147c1db33
cli-tools-over-mcp-for-tokens is a command published in the GitHub repository runnithan/claudex-setup (1 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 395 tokens. 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 commands, from other repositories
cost-optimize
You are a cloud cost optimization expert specializing in reducing infrastructure expenses while maintaining performance and reliability. Analyze cloud spending, identify savings opportunities, and implement cost-effective architectures across AWS, Azure, GCP, and OCI. Where provider-specific code appears below, adapt…
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
security-review
A security review procedure based on CWE, a list of common software weaknesses, and STRIDE, a method for identifying threats to a system.
update-counts
Update all hardcoded counts (skills, agents, marketplace repos/skills) across documentation from filesystem.
refactor
Analyze code for SOLID violations and suggest targeted improvements.