agentmods.dev

cli-anything-web:validate

A command that checks a website-connected command-line tool against a required quality checklist. It runs critical checks first, followed by broader checks and an installation smoke test.

In plain words
What is it for?
Validating critical and comprehensive standards, installing the CLI, checking its help and diagnostic commands, and running post-install checks.
Why use it?
It catches release-blocking problems in the tool’s structure, behavior, installation, and documentation before publication.

Command

216 9d ago A scan 39 tokens original MIT
View the source file ItamarZand88/CLI-Anything-WEB
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/itamarzand88/cli-anything-web/validate
Clone the repo
git clone --depth 1 https://github.com/ItamarZand88/CLI-Anything-WEB
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 868 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 $0.00039 $0.00868
Opus 5 $0.00019 $0.00434
Sonnet 5 $0.00008 $0.00174
Haiku 4.5 $0.00004 $0.00087

Measured 2d ago against content hash 7417ab0579fd, 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-web: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 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-web-plugin/commands/validate.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL: Read the Conventions First

Before validating, read ${CLAUDE_PLUGIN_ROOT}/skills/shared/CONVENTIONS.md. It is the single source of truth for every rule the checklist enforces (HARNESS.md is the navigational overview that indexes it).

CLI-Anything-Web: Validate Standards

Read the methodology overview: @${CLAUDE_PLUGIN_ROOT}/HARNESS.md

Target: $ARGUMENTS

Process

Skills used: standards (tiered checklist validation)

  1. Parse the target path to extract <app> name
  2. Resolve the agent-harness/ root and cli_web/<app>/ package path
  3. Tier 1 fail-fast first — critical checks must all pass before anything else: 
    python ${CLAUDE_PLUGIN_ROOT}/scripts/validate-checklist.py \
  <app>/agent-harness --app-name <app> --auth-type <auth-type> --tier1-only
    Non-zero exit = Tier 1 failures. Fix them and re-run before continuing.
  4. Full checklist run (both tiers; Tier 2 failures are warnings unless --strict): 
    python ${CLAUDE_PLUGIN_ROOT}/scripts/validate-checklist.py \
  <app>/agent-harness --app-name <app> --auth-type <auth-type>
  5. Run the smoke test for post-install validation: 
    python ${CLAUDE_PLUGIN_ROOT}/scripts/smoke-test.py cli-web-<app> --auth-type <auth-type>
  6. Review remaining judgment-based checks manually per the standards skill
  7. Print the report in the format shown at the bottom
  8. Exit with summary: PASS if no Tier 1 failures (report Tier 2 failures as warnings), FAIL otherwise

Prerequisites

  • npx @playwright/cli@latest --version succeeds (playwright-cli available)

Validation Checklist

Invoke the standards skill which runs the complete tiered checklist across 11 categories:

  1. Directory Structure (6 checks)
  2. Required Files (13 checks)
  3. CLI Implementation (9 checks)
  4. Core Modules (8 checks)
  5. Test Standards (8 checks)
  6. Documentation (3 checks)
  7. PyPI Packaging (5 checks)
  8. Code Quality (8 checks)
  9. REPL Quality (3 checks)
  10. Error Handling & Resilience (8 checks)
  11. UX Patterns (4 checks)

Read the full file on GitHub · 100 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 · 100 lines · 39 tokens per session scan A 7417ab0579fd

Subscribe to this mod's changes

cli-anything-web:validate is a command published in the GitHub repository ItamarZand88/CLI-Anything-WEB (216 stars, last pushed 9d ago), licensed MIT. It adds 39 tokens to every session and 868 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.

Testingagent-nativeclaude-codeclaude-code-plugincliplaywright
Related

Other commands, from other repositories

video

Video projects - list, resume, or create new.

digitalsamba/claude-code-video-toolkit · 10 tokens

brand

Brand profiles - list, edit, or create new.

digitalsamba/claude-code-video-toolkit · 10 tokens

design

Focused design session for improving video scene visuals using the frontend-design skill.

digitalsamba/claude-code-video-toolkit · 0 tokens

template

List available templates and their features.

digitalsamba/claude-code-video-toolkit · 6 tokens

qawolf-cli

Manage QA Wolf through the qawolf CLI. Use when asked to create, update, or list coverage requests, bug reports, or maintenance reports; start a run of flows or tags on the QA Wolf platform or read a run's results; list, set, or delete environment variables; manage environments, flows, or tags; request automation of…

qawolf/cli · 118 tokens

setup

Set up Poster Maker for first use.

dabodamjan/poster-maker · 7 tokens