A command that checks a CLI-Anything harness against the requirements in HARNESS.md, the project’s standards document. A harness is the code that exposes software through commands an agent can use.

Use it with a local software path or GitHub repository URL to check the harness directory, Python package layout, required files, and other project standards.

It finds structural and implementation problems before the harness is treated as ready.

validate — Command by HKUDS

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/validate

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 1,150 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01150
Opus 5	$0.00000	$0.00575
Sonnet 5	$0.00000	$0.00230
Haiku 4.5	$0.00000	$0.00115

Measured yesterday against content hash d010bd07c90e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate 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 yesterday.

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/validate.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cli-anything:validate Command

Validate a CLI harness against HARNESS.md standards and best practices.

CRITICAL: Read HARNESS.md First

Before validating, read ./HARNESS.md. It is the single source of truth for all validation checks below. Every check in this command maps to a requirement in HARNESS.md.

Usage

/cli-anything:validate <software-path-or-repo>

Arguments

<software-path-or-repo> - Required. Either:
- A local path to the software source code (e.g., /home/user/gimp, ./blender)
- A GitHub repository URL (e.g., https://github.com/GNOME/gimp, github.com/blender/blender)
If a GitHub URL is provided, the agent clones the repo locally first, then works on the local copy.

The software name is derived from the directory name. The agent locates the CLI harness at /root/cli-anything/<software-name>/agent-harness/.

What This Command Validates

1. Directory Structure

agent-harness/cli_anything/<software>/ exists (namespace sub-package)
cli_anything/ has NO __init__.py (PEP 420 namespace package)
<software>/ HAS __init__.py (regular sub-package)
core/, utils/, tests/ subdirectories present
setup.py in agent-harness/ uses find_namespace_packages

2. Required Files

README.md - Installation and usage guide
<software>_cli.py - Main CLI entry point
core/project.py - Project management
core/session.py - Undo/redo
core/export.py - Rendering/export
tests/TEST.md - Test plan and results
tests/test_core.py - Unit tests
tests/test_full_e2e.py - E2E tests
../<SOFTWARE>.md - Software-specific SOP

3. CLI Implementation Standards

Uses Click framework
Has command groups (not flat commands)
Implements --json flag for machine-readable output
Implements --project flag for project file
Has handle_error decorator for consistent error handling
Has REPL mode
Has global session state

4. Core Module Standards

project.py has: create, open, save, info, list_profiles
session.py has: Session class with undo/redo/snapshot
export.py has: render function and EXPORT_PRESETS
All modules have proper docstrings
All functions have type hints

Read the full file on GitHub · 124 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.

yesterday First seen · 124 lines · 0 tokens per session scan A d010bd07c90e

Subscribe to this mod's changes

validate is a command published in the GitHub repository HKUDS/CLI-Anything (48,669 stars, last pushed 11d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,150 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.

Documents Languages Planning

validate

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

cli-anything:validate Command

CRITICAL: Read HARNESS.md First

Usage

Arguments

What This Command Validates

1. Directory Structure

2. Required Files

3. CLI Implementation Standards

4. Core Module Standards

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement