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 skills add organvm-iv-taxis/a-i--skills --skill cli-tool-designgit clone --depth 1 https://github.com/organvm-iv-taxis/a-i--skillsWrote 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/organvm-iv-taxis/a-i--skills/cli-tool-design)<a href="https://agentmods.dev/skills/organvm-iv-taxis/a-i--skills/cli-tool-design"><img src="https://agentmods.dev/badge/skills/organvm-iv-taxis/a-i--skills/cli-tool-design/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/skills/organvm-iv-taxis/a-i--skills/cli-tool-design"><img src="https://agentmods.dev/badge/skills/organvm-iv-taxis/a-i--skills/cli-tool-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 122 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00054 | $0.01660 |
| Opus 5 | $0.00027 | $0.00830 |
| Sonnet 5 | $0.00011 | $0.00332 |
| Haiku 4.5 | $0.00005 | $0.00166 |
Grade A, and why
cli-tool-design 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Tool Design
Build command-line tools that are discoverable, composable, and pleasant to use.
Design Principles
The UNIX Philosophy Applied
- Do one thing well — Each command has a clear, singular purpose
- Compose through pipes — Support stdin/stdout for chaining
- Fail loudly — Non-zero exit codes and stderr for errors
- Be predictable — Consistent flags, consistent output format
Command Structure
program [global-options] command [command-options] [arguments]
Example:
organvm --verbose registry update --organ IV a-i--skills
Framework Selection
| Framework | Language | Best For |
|---|---|---|
| Typer | Python | Modern CLIs with type hints, auto-completion |
| Click | Python | Complex CLIs, plugins, nested groups |
| argparse | Python | Zero-dependency, stdlib-only |
| clap | Rust | High-performance, compiled CLIs |
| cobra | Go | Go microservice CLIs |
Building with Typer (Recommended for Python)
Basic Command
import typer
app = typer.Typer(help="ORGANVM system management CLI")
@app.command()
def status(
organ: str = typer.Argument(help="Organ number (I-VII or META)"),
verbose: bool = typer.Option(False, "--verbose", "-v", help="Show detailed output"),
):
"""Show the status of an organ's repositories."""
# Implementation here
Subcommand Groups
app = typer.Typer()
registry_app = typer.Typer(help="Registry operations")
app.add_typer(registry_app, name="registry")
@registry_app.command("update")
def registry_update(
organ: str = typer.Argument(help="Target organ"),
dry_run: bool = typer.Option(False, "--dry-run", "-n"),
):
"""Update registry entries for an organ."""
Rich Output Integration
from rich.console import Console
from rich.table import Table
console = Console(stderr=True) # Status to stderr
def show_repos(repos: list[dict]):
table = Table(title="Repositories")
table.add_column("Name", style="cyan")
table.add_column("Status", style="green")
table.add_column("Tier")
for repo in repos:
table.add_row(repo["name"], repo["status"], repo["tier"])
console.print(table)
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.
- 12d ago First seen · 262 lines · 54 tokens per session scan A a37cea783f6c
cli-tool-design is a skill published in the GitHub repository organvm-iv-taxis/a-i--skills (17 stars, last pushed 16d ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,660 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 2026-08-30.
Other skills, from other repositories
plugin-system
Generic plugin system for Python applications. Auto-discovery, validation, fault tolerance. Zero dependencies (Python stdlib only).
pydantic
Python data validation using type hints and runtime type checking with Pydantic v2's Rust-powered core for high-performance validation in FastAPI, Django, and configuration management.
python-cli-typer
Build production-grade Python CLIs with Typer (or Click) — subcommands, options, env config, exit codes, and testing.
domain-web
A set of guidance for building web services, which are programs that communicate over the internet through requests and responses.
gr-cli-guide
Command-line reference for @gravity-rail/cli — domain listing, CRUD patterns, output formats, and write safety. Use when scripting or exploring the API from a terminal.
printing-press
Set up a new integration, connector, or CLI binding for any API. Wrap or generate a ship-ready Go CLI from an OpenAPI, HAR, or Postman spec via the lean research -> generate -> build -> shipcheck loop. Use when the user says build a CLI, wrap this API, set up a new integration, add a connector, integrate with a…