cli-anything

A set of instructions for building, improving, testing, validating, or listing command-line tools that let agents operate graphical applications or source-code repositories.

In plain words
What is it for?
Use it to create a new CLI-Anything harness, refine an existing one, run its checks, validate it against the project standards, or list available harnesses.
Why use it?
It provides a defined process for turning software into an agent-usable command-line tool without changing the generated Python format.

Skill for Claude CodeCodex

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 skills/hkuds/cli-anything/codex-skill
Any agent
npx skills add HKUDS/CLI-Anything --skill codex-skill
Clone the repo
git clone --depth 1 https://github.com/HKUDS/CLI-Anything

Made for: Claude Code, Codex.

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,349 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 $0.00054 $0.01349
Opus 5 $0.00027 $0.00674
Sonnet 5 $0.00011 $0.00270
Haiku 4.5 $0.00005 $0.00135

Measured yesterday against content hash fb650312aed6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cli-anything 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.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/install.ps1, scripts/install.sh, tests/test_install.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

codex-skill/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLI-Anything for Codex

Use this skill when the user wants Codex to act like the CLI-Anything builder.

Read the Full Methodology First

Before implementation, use the full methodology source of truth:

  1. Read references/HARNESS.md relative to this skill directory.
  2. Read the matching mode specification under references/commands/.
  3. Read referenced files under references/guides/ only when they apply to the target.
  4. If the installed resources are unavailable and this skill is being used from a CLI-Anything repository checkout, read ../cli-anything-plugin/HARNESS.md and the resources around it.
  5. If neither local source is available, clone or download https://github.com/HKUDS/CLI-Anything and use cli-anything-plugin/HARNESS.md.
  6. Only if all full-methodology sources are unavailable, follow the condensed rules below.

The installer vendors the canonical resources from cli-anything-plugin/ into this skill so a normal Codex installation is self-contained.

Resource Map

Path Purpose
references/HARNESS.md Complete methodology and quality rules
references/commands/cli-anything.md Build-mode specification
references/commands/refine.md Refine-mode specification
references/commands/test.md Test-mode specification
references/commands/validate.md Validation checklist
references/commands/list.md Installed/generated harness discovery
references/guides/ On-demand implementation guidance
scripts/repl_skin.py Copy into generated harnesses as utils/repl_skin.py
scripts/preview_bundle.py Copy into preview-capable harnesses as utils/preview_bundle.py
scripts/skill_generator.py Generate canonical and packaged CLI skills
scripts/templates/SKILL.md.template Skill generation template used by skill_generator.py
references/docs/PREVIEW_PROTOCOL.md Shared preview bundle protocol

When reading vendored documents, apply these path remappings instead of resolving plugin paths against the current working directory:

Read the full file on GitHub · 155 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 155 lines · 54 tokens per session scan A fb650312aed6

Subscribe to this mod's changes

cli-anything is a skill published in the GitHub repository HKUDS/CLI-Anything (48,669 stars, last pushed 11d ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,349 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens