DeepSeek-Harness-Desktop: Skill for Claude Code

.agents/skills/asc-apple-ads/SKILL.md

asc-apple-ads is a skill for Claude Code, Codex from web-casa/DeepSeek-Harness-Desktop. It costs 50 tokens per session (3,216 once invoked), scanned A, a copy of asc-apple-ads, MIT.

A command-line workflow for managing Apple Ads campaigns and related account data. Apple Ads is Apple's advertising service for promoting apps in its stores, and the workflow supports both its current and older APIs.

In plain words
What is it for?
Use it to sign in, discover ad accounts, manage campaigns and targeting, upload assets, request reports, inspect recommendations, and send raw API requests. It also helps with the migration from the older Campaign Management API.
Why use it?
It helps prevent account and API mix-ups, especially when Apple Ads credentials differ from App Store Connect credentials. It also supports cautious, scriptable work with reports, targeting, assets, and campaign changes.

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-apple-ads/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-apple-ads

README.md
[![agentmods](https://agentmods.dev/badge/skills/web-casa/deepseek-harness-desktop/asc-apple-ads/github.svg)](https://agentmods.dev/skills/web-casa/deepseek-harness-desktop/asc-apple-ads)
Your own site
<a href="https://agentmods.dev/skills/web-casa/deepseek-harness-desktop/asc-apple-ads"><img src="https://agentmods.dev/badge/skills/web-casa/deepseek-harness-desktop/asc-apple-ads/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-apple-ads

Your own site · 80×15
<a href="https://agentmods.dev/skills/web-casa/deepseek-harness-desktop/asc-apple-ads"><img src="https://agentmods.dev/badge/skills/web-casa/deepseek-harness-desktop/asc-apple-ads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,216 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 $0.00050 $0.03216
Opus 5 $0.00025 $0.01608
Sonnet 5 $0.00010 $0.00643
Haiku 4.5 $0.00005 $0.00322

Measured 11d ago against content hash 2dd8b220d439, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

asc-apple-ads 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 11d 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-apple-ads — 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-apple-ads/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

asc Apple Ads

Run Apple Ads work through asc ads. Apple Ads credentials are separate from App Store Connect credentials; asc auth login does not configure Ads.

Pick the API first

  • Direct asc ads <resource> ... commands use Apple Ads Platform API v1 and an ad account ID.
  • Deprecated Campaign Management API v5 commands live under asc ads v5 ... and use an organization ID. Apple retires v5 on January 26, 2027.
  • Never substitute an org ID for an ad account ID. The CLI keeps them separate.
  • Run the exact leaf command with --help before building a request file. Platform v1 payloads and response envelopes differ from v5; the CLI does not translate them.
  • For non-interactive pipelines, pass --file - to read a JSON request body from stdin; the CLI rejects it when stdin is a terminal.
  • Resource, report, upload, and raw commands emit lossless JSON. Use jq for projections instead of asking for table or markdown output.

Authenticate and pin the account

Store both contexts when a profile must support v1 and legacy v5:

asc ads auth login \
  --name "Marketing" \
  --client-id "$ASC_ADS_CLIENT_ID" \
  --team-id "$ASC_ADS_TEAM_ID" \
  --key-id "$ASC_ADS_KEY_ID" \
  --private-key "$ASC_ADS_PRIVATE_KEY_PATH" \
  --ad-account "987654" \
  --org "123456" \
  --network

For CI, set Ads-specific variables and bypass the host keychain:

export ASC_ADS_CLIENT_ID="SEARCHADS_CLIENT_ID"
export ASC_ADS_TEAM_ID="SEARCHADS_TEAM_ID"
export ASC_ADS_KEY_ID="KEY_ID"
export ASC_ADS_PRIVATE_KEY_PATH="$HOME/.asc/apple-ads-private-key.pem"
export ASC_ADS_AD_ACCOUNT_ID="987654"
export ASC_ADS_BYPASS_KEYCHAIN=1

ASC_ADS_PRIVATE_KEY and ASC_ADS_PRIVATE_KEY_B64 also work. If another trusted process minted a short-lived token, set ASC_ADS_ACCESS_TOKEN; scoped v1 calls still need an ad account ID.

Check auth without printing a token:

asc ads auth status --validate --output json
asc ads auth discover --ads-profile "Marketing" --output json
asc ads auth doctor --output json

Read the full file on GitHub · 266 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. 11d ago First seen · 266 lines · 50 tokens per session scan A 2dd8b220d439

Subscribe to this mod's changes

asc-apple-ads is a skill published in the GitHub repository web-casa/DeepSeek-Harness-Desktop (121 stars, last pushed 6d ago), licensed MIT. It adds 50 tokens to every session and 3,216 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-apple-ads, differing in 0 lines, and is treated as a copy.