refine

A command that improves an existing command-line harness by adding coverage for more of the application's functions and usage patterns. Coverage here means how much of the application's behaviour the harness can exercise.

In plain words
What is it for?
Use it with the original local source tree to identify missing commands and tests, either broadly or for a specified functionality area.
Why use it?
It helps find areas that the first harness missed without rebuilding the whole harness. An optional focus lets the work target one feature area, such as batch processing or picture-in-picture video.

Command

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/hkuds/cli-anything/refine
Clone the repo
git clone --depth 1 https://github.com/HKUDS/CLI-Anything
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,158 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 $0.00000 $0.01158
Opus 5 $0.00000 $0.00579
Sonnet 5 $0.00000 $0.00232
Haiku 4.5 $0.00000 $0.00116

Measured 2d ago against content hash f7de3b28bad7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refine 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.

cli-anything-plugin/commands/refine.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cli-anything:refine Command

Refine an existing CLI harness to improve coverage of the software's functions and usage patterns.

CRITICAL: Read HARNESS.md First

Before refining, read ./HARNESS.md. All new commands and tests must follow the same standards as the original build. HARNESS.md is the single source of truth for architecture, patterns, and quality requirements.

Usage

/cli-anything:refine <software-path> [focus]

Arguments

  • <software-path> - Required. Local path to the software source code (e.g., /home/user/gimp, ./blender). Must be the same source tree used during the original build.

    Note: Only local paths are accepted. If you need to work from a GitHub repo, clone it first with /cli-anything, then refine.

  • [focus] - Optional. A natural-language description of the functionality area to focus on. When provided, the agent skips broad gap analysis and instead targets the specified capability area.

    Examples:

    • /cli-anything:refine /home/user/shotcut "vid-in-vid and picture-in-picture features"
    • /cli-anything:refine /home/user/gimp "all batch processing and scripting filters"
    • /cli-anything:refine /home/user/blender "particle systems and physics simulation"
    • /cli-anything:refine /home/user/inkscape "path boolean operations and clipping"

    When [focus] is provided:

    • Step 2 (Analyze Software Capabilities) narrows to only the specified area
    • Step 3 (Gap Analysis) compares only the focused capabilities against current coverage
    • The agent should still present findings before implementing, but scoped to the focus area

What This Command Does

This command is used after a CLI harness has already been built with /cli-anything. It analyzes gaps between the software's full capabilities and what the current CLI covers, then iteratively expands coverage. If a [focus] is given, the agent narrows its analysis and implementation to that specific functionality area.

Step 1: Inventory Current Coverage

  • Read the existing CLI entry point (<software>_cli.py) and all core modules
  • List every command, subcommand, and option currently implemented
  • Read the existing test suite to understand what's tested
  • Build a coverage map: { function_name: covered | not_covered }

Read the full file on GitHub · 105 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 · 105 lines · 0 tokens per session scan A f7de3b28bad7

Subscribe to this mod's changes

refine is a command published in the GitHub repository HKUDS/CLI-Anything (48,809 stars, last pushed 12d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,158 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 2026-08-30.