document-cli-tool

Research and document AI CLI tool capabilities through testing and experimentation.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/jnarowski/agentcmd/document-cli-tool
Clone the repo
git clone --depth 1 https://github.com/jnarowski/agentcmd

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,954 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.03954
Opus 5 $0.00005 $0.01977
Sonnet 5 $0.00002 $0.00791
Haiku 4.5 $0.00001 $0.00395

Measured today against content hash 0ba01421b011, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

document-cli-tool 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 today.

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.

.claude/commands/document-cli-tool.md · 816 lines

How it starts

The opening of the file, as written. The whole thing — 816 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document CLI Tool

Comprehensive research and documentation of an AI CLI tool's capabilities, output formats, session management, file operations, and permission modes. This command performs hands-on testing and generates detailed technical documentation for SDK integration.

Variables

  • $cli-name: $1 (required) - The name of the CLI tool to explore (e.g., "gemini", "codex", "cursor")

Instructions

  • Be thorough - actually run commands and capture real terminal output
  • Document exact command syntax, flags, and output formats
  • Test edge cases and failure modes
  • Compare capabilities to Claude Code and Cursor CLI
  • Focus on technical details needed for SDK integration
  • Save all findings to .agent/docs/${cli-name}.md (lowercase cli name)

Workflow

  1. Initial Discovery

    • Check if CLI is installed (which ${cli-name} or platform equivalent)
    • If not installed, search for installation instructions online
    • Run help commands: ${cli-name} --help, ${cli-name} -h, ${cli-name} help
    • Capture complete help output
  2. Command Reference Testing

    • Test all available commands and subcommands
    • Document command syntax, required/optional flags
    • Capture example output for each command
    • Note any environment variables or configuration files
  3. Output Format Analysis

    • Test different output formats (text, JSON, JSONL, stream-json, etc.)
    • Run same prompt with each format and capture exact output
    • Identify message boundaries and event types
    • Document parsing patterns and delimiters
    • Test: ${cli-name} "hello world" --output-format json
    • Test: ${cli-name} "hello world" --output-format stream-json
    • Test: ${cli-name} "hello world" (default format)
  4. Session Management Deep Dive

    • Create a test session: ${cli-name} "test prompt" --session test-session-1
    • Identify session ID format and constraints
    • Find session storage location (files, database, config dirs)
    • Inspect session file structure and schema
    • Resume session with new prompt: ${cli-name} "follow-up" --session test-session-1
    • Test session persistence across restarts
    • List all sessions (if command available)
    • Document session lifecycle and cleanup

Read the full file on GitHub · 816 lines

Changes

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.

  1. today First seen · 816 lines · 11 tokens per session scan A 0ba01421b011

Subscribe to this mod's changes

document-cli-tool is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 11 tokens to every session and 3,954 once invoked, about $0.0001 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 2026-09-01.