Agent skill

Agent CLI

by glebis in glebis/claude-skills

Add agent-friendly --json NDJSON output to Python CLI scripts, or scaffold a complete cliutils package for a project.

MITAuto-check passedDevelopment

Install Agent CLI

skills CLI
$ npx skills add glebis/claude-skills --skill agent-cli -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install glebis/claude-skills agent-cli --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/glebis/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent-cli .claude/skills/agent-cli && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-cli
GitHub stars
388
Token cost
~3k tokens
SKILL.md length
741 words
Files
3 (incl. references)
Skills in repo
91
Repo updated
First seen
Licence
MIT

At a glance

Add agent-friendly --json NDJSON output to Python CLI scripts, or scaffold a complete cliutils package for a project.

  • Works in 4 steps: Scan for output points → Add the import and flag → Replace each output point → …
  • The user wants to make scripts machine-readable for AI agents
  • SKILL.md covers Two Modes, Core Architecture, The cli_utils.py Reference… and Converting a Script — Step by…, plus 4 more sections
  • Calls python and pip; reaches github.com

What it does

Agent CLI is an agent skill from glebis/claude-skills. Add agent-friendly --json NDJSON output to Python CLI scripts, or scaffold a complete cliutils package for a project. Use this skill when the user wants to make scripts machine-readable for AI agents, add --json flags, convert print statements to structured JSON, build a CLI helper library, create an open-source CLI-for-agents package, add structured logging, or make CLI output machine-readable. Also use when the user mentions NDJSON, structured CLI output, agent-friendly CLI, non-interactive scripts, or JSON I/O…

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `evals/evals.json` and `references/best-practices.md`).

It sits in Development, covering Observability and Project scaffolding. It works with Python. The repository describes itself as: Collection of Claude Code skills for enhanced AI workflows. The licence is MIT.

When your agent uses it

  • The user wants to make scripts machine-readable for AI agents
  • Add --json flags
  • Convert print statements to structured JSON
  • Build a CLI helper library

Example prompts

  • “/agent-cli”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Scan for output points
  2. Add the import and flag
  3. Replace each output point
  4. Verify

What it can do on your machine

Read from SKILL.md and the folder at commit 7524dff. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent CLI loads about 3k tokens when it runs, and up to ~5.9k if it reads all its reference files. Until then it costs about 136 tokens; SKILL.md has 741 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~136
When it runs · the whole SKILL.md, loaded when a task matches
~3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from glebis/claude-skills at commit 7524dff, republished under its MIT licence (© glebis). 741 words, ~2,987 tokens.

Download SKILL.mdSave it as .claude/skills/agent-cli/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
agent-cli
description
Add agent-friendly --json NDJSON output to Python CLI scripts, or scaffold a complete cli_utils package for a project. Use this skill when the user wants to make scripts machine-readable for AI agents, add --json flags, convert print statements to structured JSON, build a CLI helper library, create an open-source CLI-for-agents package, add structured logging, or make CLI output machine-readable. Also use when the user mentions NDJSON, structured CLI output, agent-friendly CLI, non-interactive scripts, or JSON I/O for automation.

Agent-Friendly CLI Builder

Convert Python CLI scripts from human-only output to agent-consumable NDJSON, or scaffold a complete cli_utils package ready for open-source distribution.

Two Modes

Mode A: Convert an existing script

When the user points at a script and says "make this agent-friendly" or "add --json":

  1. Scan the script for output points
  2. Generate cli_utils.py if the project doesn't have one
  3. Replace all output with structured helpers
  4. Verify no raw output leaks in JSON mode
Mode B: Scaffold a complete package

When the user says "create a cli_utils package" or wants an open-source library:

  1. Scaffold a full Python package with pyproject.toml, tests, license, README
  2. Include all helpers: json_log, json_error, die, log, add_json_flag, enable_json, is_json
  3. Add pytest test suite with full coverage
  4. Add MIT license (or ask user preference)

Core Architecture

The fundamental pattern: every script gets a --json flag. When active, all stdout becomes newline-delimited JSON (NDJSON). Each line is a self-contained JSON object with a standard envelope.

The NDJSON Event Envelope

Every JSON line has at minimum:

json
{"event": "ready", "ts": "2026-04-30T14:00:00+00:00", "pid": 1234, "port": 8765}
  • event — what happened (snake_case string)
  • ts — ISO 8601 UTC timestamp
  • Additional fields are event-specific kwargs
Why This Design
  • NDJSON over JSON arrays: processable line-by-line, one bad line doesn't break the stream, works with grep/jq, low memory for long-running processes
  • --json opt-in over default: preserves human DX, doesn't break existing scripts or habits
  • Global mode flag over per-call checks: set once at startup, every helper respects it automatically
  • die() over repeated if/else: the pattern if is_json(): json_error(); sys.exit(1) else: print(); sys.exit() appears constantly — die() collapses it to one line

The cli_utils.py Reference Implementation

When generating cli_utils.py, produce exactly this (adapt only if the project has specific needs):

python
"""Shared helpers for JSON CLI output."""
import json
import os
import sys
from datetime import datetime, timezone

_json_mode = False

def enable_json():
    global _json_mode
    _json_mode = True

def is_json():
    return _json_mode

def json_log(event: str, **kwargs):
    """Emit one NDJSON line to stdout."""
    obj = {"event": event, "ts": datetime.now(timezone.utc).isoformat(), **kwargs}
    print(json.dumps(obj, default=str), flush=True)

def json_error(message: str, **kwargs):
    """Emit a structured error event."""
    json_log("error", message=message, **kwargs)

def die(message: str, code: int = 1, **kwargs):
    """Print error and exit — JSON or human depending on mode."""
    if _json_mode:
        json_error(message, **kwargs)
    else:
        print(message, file=sys.stderr)
    sys.exit(code)

def add_json_flag(parser):
    """Add --json flag to an argparse parser."""
    parser.add_argument("--json", action="store_true",
                        help="NDJSON output for agent consumption")

def log(message: str, **json_kwargs):
    """Print human message normally, or emit JSON event if --json is active."""
    if _json_mode:
        json_log(json_kwargs.pop("event", "info"), message=message, **json_kwargs)
    else:
        print(message)

def json_ready(**kwargs):
    """Emit the readiness signal — only in JSON mode. Call early in daemon startup."""
    if _json_mode:
        json_log("ready", pid=os.getpid(), **kwargs)

Converting a Script — Step by Step

Step 1: Scan for output points

Search the target script for all places that produce output or exit:

bash
grep -n 'print(\|sys\.exit\|exit(\|input(\|os\.system.*say' TARGET.py

Categorize each hit:

  • Informational print → replace with log(message, event="descriptive_name")
  • Error + exit → replace with die(message)
  • Status line with \r → replace with if is_json(): json_log("status", ...) else: print("\r...", end="", flush=True)
  • Interactive input() → guard with if not is_json(): or add --no-interactive flag
  • Side effects (say, osascript, notifications) → guard with if not is_json():
  • Import-time errors (before argparse runs) → use sys.exit("message") (writes to stderr)
Step 2: Add the import and flag

At the top of the script, after existing imports:

python
from cli_utils import add_json_flag, enable_json, is_json, json_log, log, die

In the if __name__ == "__main__" block, add to argparse:

python
add_json_flag(parser)
args = parser.parse_args()
if args.json:
    enable_json()
Step 3: Replace each output point

Apply the categorization from Step 1. Key patterns:

Simple informational:

python
# Before
print(f"Connected to {device}")

# After
log(f"Connected to {device}", event="connected", device=device)

Error + exit:

python
# Before
print("Device not found")
sys.exit(1)

# After
die("Device not found")

Daemon readiness (first output after initialization):

python
# Before
print(f"Server running on port {port}")

# After — json_ready() only emits in JSON mode, so always call it + human fallback
json_ready(port=port)
log(f"Server running on port {port}", event="ready", port=port)

Status lines (\r overwrite):

python
# Before
print(f"\r  HR {hr} RMSSD {rmssd:.1f}", end="", flush=True)

# After
if is_json():
    json_log("status", hr=hr, rmssd=rmssd)
else:
    print(f"\r  HR {hr} RMSSD {rmssd:.1f}", end="", flush=True)

Human-only output (banners, usage examples):

python
if not is_json():
    print("Usage: send {\"type\": \"join\", \"name\": \"Alice\"}")
Step 4: Verify
  1. Run python script.py --help — confirm --json flag appears
  2. Run python script.py --json — confirm first line is valid JSON
  3. Grep for remaining raw print( calls — ensure each is guarded or intentional
Show full SKILL.md (284 more words)Show less

Event Name Conventions

Use snake_case, be descriptive, keep them grep-friendly:

CategoryEvents
Lifecycleready, shutdown, connected, disconnected
Datahr, status, metric, heartbeat
Errorserror, retry
Actionsrecording_started, recording_stopped, preset_change
Progressscanning, connecting, downloading, importing

Scaffolding an Open-Source Package

When the user wants a distributable package, scaffold this structure:

cli-utils-agent/
├── pyproject.toml
├── LICENSE                  # MIT by default, ask user
├── README.md
├── src/
│   └── cli_utils_agent/
│       ├── __init__.py      # re-exports all public API
│       └── core.py          # the implementation
├── tests/
│   ├── __init__.py
│   ├── test_json_log.py
│   ├── test_die.py
│   ├── test_log.py
│   └── test_add_json_flag.py
└── .github/
    └── workflows/
        └── test.yml         # CI with pytest
__init__.py — re-export public API
python
# src/cli_utils_agent/__init__.py
from .core import (
    enable_json, is_json, json_log, json_error, die,
    add_json_flag, log, json_ready,
)

__all__ = [
    "enable_json", "is_json", "json_log", "json_error", "die",
    "add_json_flag", "log", "json_ready",
]
README.md template

Generate a README with: project name, one-line description, install instructions (pip install cli-utils-agent), quick usage example showing add_json_flag + enable_json + log(), API reference table listing all exports with one-line descriptions, and a link to the research background.

pyproject.toml template
toml
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[project]
name = "cli-utils-agent"
version = "0.1.0"
description = "Add agent-friendly --json NDJSON output to any Python CLI"
readme = "README.md"
license = "MIT"
requires-python = ">=3.10"
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "License :: OSI Approved :: MIT License",
    "Programming Language :: Python :: 3",
    "Topic :: Software Development :: Libraries",
]

[project.urls]
Homepage = "https://github.com/USER/cli-utils-agent"

[tool.hatch.build.targets.wheel]
packages = ["src/cli_utils_agent"]
Test suite

Use capsys for stdout capture, pytest.raises(SystemExit) for die(). Example:

python
# tests/test_json_log.py
import json
from cli_utils_agent import json_log, enable_json, is_json

def test_json_log_writes_ndjson(capsys):
    json_log("ready", port=8765, pid=42)
    line = capsys.readouterr().out.strip()
    obj = json.loads(line)
    assert obj["event"] == "ready"
    assert obj["port"] == 8765
    assert "ts" in obj

# tests/test_die.py
import json
import pytest
from cli_utils_agent import die, enable_json
from cli_utils_agent import core as _core

def test_die_human_mode(capsys):
    _core._json_mode = False
    with pytest.raises(SystemExit) as exc:
        die("something broke")
    assert exc.value.code == 1
    assert "something broke" in capsys.readouterr().err

def test_die_json_mode(capsys):
    _core._json_mode = True
    try:
        with pytest.raises(SystemExit):
            die("something broke", code=10)
        obj = json.loads(capsys.readouterr().out.strip())
        assert obj["event"] == "error"
        assert obj["message"] == "something broke"
    finally:
        _core._json_mode = False

Cover: json_log, json_error, die, log, add_json_flag, enable_json/is_json, json_ready.

GitHub Actions CI
yaml
# .github/workflows/test.yml
name: Tests
on: [push, pull_request]
jobs:
  test:
    runs-on: ubuntu-latest
    strategy:
      matrix:
        python-version: ["3.10", "3.11", "3.12", "3.13"]
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with:
          python-version: ${{ matrix.python-version }}
      - run: pip install -e ".[dev]"
      - run: pytest -v

Add dev dependencies to pyproject.toml:

toml
[project.optional-dependencies]
dev = ["pytest>=8.0"]

Checklist — Run Before Declaring Done

After converting a script or creating a package:

  • --help shows --json flag
  • Running with --json produces valid NDJSON (every line is parseable JSON)
  • First JSON line from daemons has "event": "ready"
  • Error paths emit "event": "error" with non-zero exit code
  • No raw print() can fire when --json is active
  • Import-time errors (missing deps) use sys.exit("message") not print()
  • Interactive prompts are guarded
  • Side effects (voice, notifications) are guarded
  • Human output is preserved when --json is NOT passed
  • Unhandled exceptions don't leak tracebacks to stdout in JSON mode (wrap main in try/except, emit json_error)
  • Tests pass (if package mode)
  • Package builds cleanly: python -m build (if package mode)
  • Install in clean venv and import works (if package mode)

Further Reading

Read references/best-practices.md when you need:

  • Heartbeat patterns for liveness detection (section 2.4)
  • Exit code conventions and string error codes (section 2.3)
  • Schema introspection with --schema (section 2.5)
  • CLI vs MCP decision matrix (section 2.7)
  • Token efficiency tips for agent consumption (section 5)

© glebis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in agent-cli of glebis/claude-skills.

  • SKILL.md
  • evals/evals.json
  • references/best-practices.md

Open the folder on GitHubat commit 7524dff

Compare with similar skills

Agent CLI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent CLI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent CLI this skillglebis/claude-skills388—~3kAutomated safety check: PassMIT
Agent Observability Experiment Bootstrapdatadog-labs/agent-skills177—~2.3kAutomated safety check: PassMIT
AzureML Project ScaffoldingKilo-Org/kilo-marketplace189—~3.1kAutomated safety check: NotesMIT
LoopX Performance Diagnosisloopx-project/loopx6.2k—~880Automated safety check: PassApache-2.0
Debugging Techniquesancoleman/ai-design-components526—~3.3kAutomated safety check: PassMIT
Project Initathola/claude-night-market342—~1.2kAutomated safety check: PassMIT

Similar skills

  • Bootstrap a reproducible LLM Observability experiment through the Python ddtrace SDK or the Node dd-trace SDK.

    177 GitHub stars~2.3k tokensUpdated 5 days ago
    DevOps & CloudAuto-check passed
  • AzureML Project Scaffolding

    Kilo-Org/kilo-marketplace

    Sets up and maintains AzureML-ready Python projects as uv workspaces with devcontainers, a Makefile and job YAML, so local runs match cloud jobs and experiments stay reproducible.

    189 GitHub stars~3.1k tokensUpdated 9 days ago
    DevelopmentAuto-check: notes
  • LoopX Performance Diagnosis

    loopx-project/loopx

    Profiles a slow command or runtime you own with the right profiler for its language, using uninstrumented baseline timings and keeping raw profiling evidence local and private.

    6.2k GitHub stars~880 tokensUpdated today
    DevelopmentAuto-check passed
  • Debugging Techniques

    ancoleman/ai-design-components

    Debugging workflows for Python (pdb, debugpy), Go (delve), Rust (lldb), and Node.js, including container debugging (kubectl debug, ephemeral containers) and production-safe debugging techniques with…

    526 GitHub stars~3.3k tokensUpdated 10 mo ago
    DevelopmentAuto-check passed
  • Project Init

    athola/claude-night-market

    Scaffolds new projects with git, CI/CD workflows, pre-commit hooks, and build config.

    342 GitHub stars~1.2k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Builds or extends a custom Mirage virtual filesystem adapter for an API, database, object store or app data, with a working mount configuration and filesystem tests.

    3.7k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed

More from glebis/claude-skills

All 91 skills in this repo
  • Runs a human-first workflow for labeling PII spans in a transcript, then scores inter-annotator agreement and drafts an adjudicated gold set.

    388 GitHub stars~1.3k tokensUpdated 11 days ago
    Auto-check passed
  • Automates a dedicated, logged-in Chrome instance per profile without ever closing the user's own open tabs or browser windows.

    388 GitHub stars~973 tokensUpdated 11 days ago
    Auto-check passed
  • Deep Research

    glebis/claude-skills

    This skill should be used when conducting comprehensive research on any topic using the OpenAI Deep Research API.

    388 GitHub stars~2.6k tokensUpdated 11 days ago
    Auto-check: notes
  • Elimination Research

    glebis/claude-skills

    This skill should be used for elimination-style research where the user wants to choose from a shortlist of products, tools, services, vendors, or other options using explicit criteria, numeric…

    388 GitHub stars~1.6k tokensUpdated 11 days ago
    Auto-check passed
  • Narrated HTML Presentations

    glebis/claude-skills

    Generates a self-contained HTML presentation with article and slides modes, ElevenLabs voiceover narration and optional GPT Image 2 illustrations.

    388 GitHub stars~2.3k tokensUpdated 11 days ago
    Auto-check: notes
  • Writes fictional but realistic coaching or therapy session transcripts for evals, demos and few-shot examples, in several modalities and export formats.

    388 GitHub stars~2.9k tokensUpdated 11 days ago
    Auto-check passed

Works with

Questions about Agent CLI

What does Agent CLI do?

Add agent-friendly --json NDJSON output to Python CLI scripts, or scaffold a complete cliutils package for a project. Agent CLI is an agent skill from glebis/claude-skills. Add agent-friendly --json NDJSON output to Python CLI scripts, or scaffold a complete cliutils package for a project.

When should I use Agent CLI?

Agent CLI fits situations like: the user wants to make scripts machine-readable for AI agents; add --json flags; convert print statements to structured JSON; build a CLI helper library.

How do I install Agent CLI in Claude Code?

Run `npx skills add glebis/claude-skills --skill agent-cli -a claude-code`. Or copy the skill folder (agent-cli in glebis/claude-skills) into .claude/skills/agent-cli in your project. Claude Code loads it when a task matches its description.

How do I install Agent CLI in Codex?

Run `npx skills add glebis/claude-skills --skill agent-cli -a codex`. Or copy the skill folder (agent-cli in glebis/claude-skills) into .agents/skills/agent-cli in your project. Codex loads it when a task matches its description.

Can I use Agent CLI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add glebis/claude-skills --skill agent-cli -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-cli, .gemini/skills/agent-cli, .github/skills/agent-cli and .opencode/skills/agent-cli in your project.

What does Agent CLI need to run?

Going by SKILL.md and its folder, Agent CLI needs the command-line tools its instructions call (python and pip). Our summary lists: Python 3.

Does Agent CLI access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Agent CLI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent CLI use?

Agent CLI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent CLI use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.9k tokens, read only when the agent opens those files.

What are the alternatives to Agent CLI?

Skills that share tags, products or a category with Agent CLI: Agent Observability Experiment Bootstrap (datadog-labs/agent-skills, 177 stars), AzureML Project Scaffolding (Kilo-Org/kilo-marketplace, 189 stars), LoopX Performance Diagnosis (loopx-project/loopx, 6.2k stars) and Debugging Techniques (ancoleman/ai-design-components, 526 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent CLI?

glebis (a GitHub user) maintains it in glebis/claude-skills, which has 388 GitHub stars. The repository holds 91 skills in this directory. The repository was last updated on September 26, 2026.

Source: glebis/claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.