DeepSeek-Harness-Desktop: Skill for Claude Code

.agents/skills/asc-subscription-localization/SKILL.md

asc-subscription-localization is a skill for Claude Code, Codex from web-casa/DeepSeek-Harness-Desktop. It costs 60 tokens per session (2,187 once invoked), scanned A, a copy of asc-subscription-localization, MIT.

A command-line workflow for translating subscription, subscription-group, and in-app-purchase names and supported descriptions across App Store languages. It uses App Store Connect and supports newer version-specific resources.

In plain words
What is it for?
Use it to create or update localizations for existing subscriptions, subscription groups, and in-app purchases after authentication and app identifiers are configured.
Why use it?
It avoids repeatedly entering the same product text for each language in the App Store Connect interface.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is web-casa/DeepSeek-Harness-Desktop's own configuration. It tells Claude Code and Codex how to work on DeepSeek-Harness-Desktop itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DeepSeek-Harness-Desktop configures →

Reuse

Borrowing it

Nothing to install: this file belongs to web-casa/DeepSeek-Harness-Desktop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/web-casa/DeepSeek-Harness-Desktop/main/.agents/skills/asc-subscription-localization/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/web-casa/DeepSeek-Harness-Desktop

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for asc-subscription-localization

README.md
[![agentmods](https://agentmods.dev/badge/skills/web-casa/deepseek-harness-desktop/asc-subscription-localization/github.svg)](https://agentmods.dev/skills/web-casa/deepseek-harness-desktop/asc-subscription-localization)
Your own site
<a href="https://agentmods.dev/skills/web-casa/deepseek-harness-desktop/asc-subscription-localization"><img src="https://agentmods.dev/badge/skills/web-casa/deepseek-harness-desktop/asc-subscription-localization/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for asc-subscription-localization

Your own site · 80×15
<a href="https://agentmods.dev/skills/web-casa/deepseek-harness-desktop/asc-subscription-localization"><img src="https://agentmods.dev/badge/skills/web-casa/deepseek-harness-desktop/asc-subscription-localization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,187 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 5.1 $0.00060 $0.02187
Opus 5 $0.00030 $0.01094
Sonnet 5 $0.00012 $0.00437
Haiku 4.5 $0.00006 $0.00219

Measured 10d ago against content hash bffc4d28b7ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

asc-subscription-localization 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 10d 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.

Origin

This is a copy

100% identical to asc-subscription-localization — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/asc-subscription-localization/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

asc subscription localization

Use this skill to bulk-create or bulk-update display names and, where supported, descriptions for subscriptions, subscription groups, and in-app purchases across all App Store Connect locales. This eliminates the tedious manual process of clicking through each language in App Store Connect to set the same display name.

Preconditions

  • Auth configured (asc auth login or ASC_* env vars).
  • Know your app ID (ASC_APP_ID or --app).
  • Subscription groups and subscriptions already exist.

Choose the API scope first

API 4.4.1 adds discrete versions for IAPs, subscriptions, and subscription groups. A version ID is different from its product, subscription, or group ID.

  • Use asc ... versions localizations ... for all new localization work.
  • Do not use the product- or group-scoped v1 localization commands. API 4.4.1 deprecates those resources, and the CLI now emits migration warnings for their compatibility commands.
  • Never pass a product, subscription, or group ID to a version-scoped command.

Resolve or create versions before localizing them:

asc iap versions list --iap-id "IAP_ID" --state PREPARE_FOR_SUBMISSION --paginate --output table
asc subscriptions versions list --subscription-id "SUB_ID" --state PREPARE_FOR_SUBMISSION --paginate --output table
asc subscriptions groups versions list --group-id "GROUP_ID" --state PREPARE_FOR_SUBMISSION --paginate --output table

Branch independently on each list result: zero matches means create, one means reuse that version ID, and more than one means stop and require an explicit version ID. Run each command below only for its zero-match branch:

# If and only if the IAP version list returned zero matches:
asc iap versions create --iap-id "IAP_ID" --output json
# If and only if the subscription version list returned zero matches:
asc subscriptions versions create --subscription-id "SUB_ID" --output json
# If and only if the group version list returned zero matches:
asc subscriptions groups versions create --group-id "GROUP_ID" --output json

Read the full file on GitHub · 192 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. 10d ago First seen · 192 lines · 60 tokens per session scan A bffc4d28b7ec

Subscribe to this mod's changes

asc-subscription-localization is a skill published in the GitHub repository web-casa/DeepSeek-Harness-Desktop (119 stars, last pushed 5d ago), licensed MIT. It adds 60 tokens to every session and 2,187 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to asc-subscription-localization, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

competitive-pricing

Research competitor pricing strategies by extracting pricing pages, comparing product listings on Google Shopping and Amazon, and analyzing market positioning. Produces pricing benchmarks, tier comparisons, and feature-per-price analysis.

sandbaseai/sandbase-skills · 41 tokens

content-translator

Translate text content between languages with high quality and natural phrasing. Covers document translation, content localization, and multi-language research support for teams working across language barriers.

sandbaseai/sandbase-skills · 36 tokens

product-intelligence

Research products across Amazon, Google Shopping, and Xiaohongshu to understand pricing, reviews, market positioning, and consumer sentiment. Covers competitive product analysis, pricing benchmarks, feature comparison, and customer satisfaction signals.

sandbaseai/sandbase-skills · 46 tokens

product-review-extractor

Extract and analyze product reviews from e-commerce and review sites. Aggregates ratings, identifies common themes in positive and negative feedback, and surfaces actionable product insights from customer voices across platforms.

sandbaseai/sandbase-skills · 41 tokens

tauri-expert

Expert in Tauri framework, Rust backend, web frontend integration, and lightweight desktop applications. Use when the user mentions desktop, Rust, web, cross platform, or performance, or when the task involves Tauri Architecture, Tauri vs Electron, Core Components, or Security Features.

personamanagmentlayer/pcl · 61 tokens

skill_creator

An interactive workflow for creating, importing, and adapting Tiangong skills, which are instruction packages for an AI agent.

silent-rs/silent-Tiangong · 0 tokens