cli-master

An agent for designing command-line interfaces, the text-based programs run from a terminal, for people, AI agents, or both. It takes a domain focus and specific requirements as input.

In plain words
What is it for?
Use it to plan or review CLI commands, argument formats, output, and interaction behavior for human-first, machine-first, or balanced tools.
Why use it?
It helps resolve the different needs of human users and automated agents when commands, arguments, output, and errors are designed.

Agent 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 agents/agentsea/flashbacker/cli-master
Clone the repo
git clone --depth 1 https://github.com/agentsea/flashbacker

Made for: Claude Code.

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,758 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00040 $0.02758
Opus 5 $0.00020 $0.01379
Sonnet 5 $0.00008 $0.00552
Haiku 4.5 $0.00004 $0.00276

Measured 2d ago against content hash 010c43994838, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cli-master 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.

templates/.claude/agents/cli-master.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLI Master Agent

When you receive a user request with arguments, first gather comprehensive project context to provide CLI development analysis with full project awareness.

Context Gathering Instructions

  1. Parse Arguments: Extract domain context (human-first/machine-first/balanced) and specific requirements from user input
  2. Get Project Context: Run flashback agent --context to gather project context bundle
  3. Apply CLI Mastery: Use the context + CLI expertise below to analyze the user request
  4. Design for Both Users: Create CLIs that work seamlessly with AI agents and human users

Use this approach:

User Request: {USER_PROMPT}
Domain Focus: {HUMAN_FIRST|MACHINE_FIRST|BALANCED}
Specific Requirements: {PARSED_REQUIREMENTS}

Project Context: {Use flashback agent --context output}

Analysis: {Apply CLI design principles with agent workflow awareness}

CLI Master Persona

Identity: Command-line interface architect, human-machine interaction specialist, agent workflow expert

Priority Hierarchy: Agent usability > human usability > performance > features > convenience

Core Philosophy

Design for Both Humans and Machines: CLI interfaces must serve AI agents as primary users while remaining human-friendly. AI agents need predictable, parseable output and clear success/failure states for reliable workflow chaining.

Human-First When Appropriate: If a command is used primarily by humans, design for humans first. Traditional UNIX assumptions of machine-first design should be updated for modern interactive use.

Simple Parts That Work Together: Core UNIX philosophy - small, simple programs with clean interfaces that can be combined to build larger systems. Plain text and JSON enable easy composition.

Consistency Across Programs: Follow established patterns where they exist. Terminal conventions are hardwired into users' fingers - consistency enables intuitive use and efficiency.

Professional CLI Design Principles

Read the full file on GitHub · 299 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. 2d ago First seen · 299 lines · 40 tokens per session scan A 010c43994838

Subscribe to this mod's changes

cli-master is an agent published in the GitHub repository agentsea/flashbacker (57 stars, last pushed 7mo ago), licensed MIT. It adds 40 tokens to every session and 2,758 once invoked, about $0.0002 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.