Blitz is a native macOS application that connects AI agents to App Store Connect for managing and submitting iOS apps. Developers use it to control parts of the iOS release process, including simulator runs, in-app purchases, screenshots, TestFlight testers, and review submissions. The catalogue includes skills, an instruction, and an MCP connection for operating Blitz.
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.
npx skills add blitzdotdev/blitz-mac --skill asc-app-create-uigit clone --depth 1 https://github.com/blitzdotdev/blitz-macWrote 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.
[](https://agentmods.dev/skills/blitzdotdev/blitz-mac/asc-app-create-ui)<a href="https://agentmods.dev/skills/blitzdotdev/blitz-mac/asc-app-create-ui"><img src="https://agentmods.dev/badge/skills/blitzdotdev/blitz-mac/asc-app-create-ui/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.
<a href="https://agentmods.dev/skills/blitzdotdev/blitz-mac/asc-app-create-ui"><img src="https://agentmods.dev/badge/skills/blitzdotdev/blitz-mac/asc-app-create-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 31 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 149 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 5.1 | $0.00019 | $0.01576 |
| Opus 5.5 | $0.00008 | $0.00630 |
| Sonnet 5.5 | $0.00004 | $0.00315 |
| Haiku 4.5 | $0.00002 | $0.00158 |
Grade A, and why
asc-app-create-ui scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import json, os, urllib.request, sys How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create an App Store Connect app using Apple's iris API. Authentication is handled via a web session file at ~/.blitz/asc-agent/web-session.json managed by Blitz.
Extract from the conversation context:
bundleId— the bundle identifier (e.g.com.blitz.myapp)sku— the SKU string (may be provided; if missing, generate one from the app name)
Workflow
1. Check for an existing web session
test -f ~/.blitz/asc-agent/web-session.json && echo "SESSION_EXISTS" || echo "NO_SESSION"
- If
NO_SESSION: call theasc_web_authMCP tool first. Wait for it to complete before proceeding. - If
SESSION_EXISTS: proceed.
2. Ask the user for the primary language
Ask what primary language/locale the app should use. Common choices: en-US (English US), en-GB (English UK), ja (Japanese), zh-Hans (Simplified Chinese), ko (Korean), fr-FR (French), de-DE (German).
3. Derive the app name
Take the last component of the bundle ID after the final ., capitalize the first letter. Confirm with the user.
4. Create the app via iris API
Use the following self-contained script. Replace BUNDLE_ID, SKU, APP_NAME, and LOCALE with the resolved values. Do not print or log cookies.
Key differences from the public REST API:
- Uses
appstoreconnect.apple.com/iris/v1/(notapi.appstoreconnect.apple.com) - Authenticated via web session cookies (not JWT)
- Uses
appInfosrelationship (notbundleIdrelationship) - App name goes on
appInfoLocalizations(notappStoreVersionLocalizations) - Uses
${new-...}placeholder IDs for inline-created resources
python3 -c "
import json, os, urllib.request, sys
BUNDLE_ID = 'BUNDLE_ID_HERE'
SKU = 'SKU_HERE'
APP_NAME = 'APP_NAME_HERE'
LOCALE = 'LOCALE_HERE'
session_path = os.path.expanduser('~/.blitz/asc-agent/web-session.json')
if not os.path.isfile(session_path):
print('ERROR: No web session found. Call asc_web_auth MCP tool first.')
sys.exit(1)
with open(session_path) as f:
raw = f.read()
store = json.loads(raw)
session = store['sessions'][store['last_key']]
cookie_str = '; '.join(
(f'{c[\"name\"]}=\"{c[\"value\"]}\"' if c['name'].startswith('DES') else f'{c[\"name\"]}={c[\"value\"]}')
for cl in session['cookies'].values() for c in cl
if c.get('name') and c.get('value')
)
headers = {
'Content-Type': 'application/json',
'Accept': 'application/json',
'X-Requested-With': 'XMLHttpRequest',
'Origin': 'https://appstoreconnect.apple.com',
'Referer': 'https://appstoreconnect.apple.com/',
'Cookie': cookie_str
}
create_body = json.dumps({
'data': {
'type': 'apps',
'attributes': {
'bundleId': BUNDLE_ID,
'sku': SKU,
'primaryLocale': LOCALE,
},
'relationships': {
'appStoreVersions': {
'data': [{'type': 'appStoreVersions', 'id': '\${new-appStoreVersion-1}'}]
},
'appInfos': {
'data': [{'type': 'appInfos', 'id': '\${new-appInfo-1}'}]
}
}
},
'included': [
{
'type': 'appStoreVersions',
'id': '\${new-appStoreVersion-1}',
'attributes': {'platform': 'IOS', 'versionString': '1.0'},
'relationships': {
'appStoreVersionLocalizations': {
'data': [{'type': 'appStoreVersionLocalizations', 'id': '\${new-appStoreVersionLocalization-1}'}]
}
}
},
{
'type': 'appStoreVersionLocalizations',
'id': '\${new-appStoreVersionLocalization-1}',
'attributes': {'locale': LOCALE}
},
{
'type': 'appInfos',
'id': '\${new-appInfo-1}',
'relationships': {
'appInfoLocalizations': {
'data': [{'type': 'appInfoLocalizations', 'id': '\${new-appInfoLocalization-1}'}]
}
}
},
{
'type': 'appInfoLocalizations',
'id': '\${new-appInfoLocalization-1}',
'attributes': {'locale': LOCALE, 'name': APP_NAME}
}
]
}).encode()
req = urllib.request.Request(
'https://appstoreconnect.apple.com/iris/v1/apps',
data=create_body, method='POST', headers=headers)
try:
resp = urllib.request.urlopen(req)
result = json.loads(resp.read().decode())
app_id = result['data']['id']
print(f'App created successfully!')
print(f'App ID: {app_id}')
print(f'Bundle ID: {BUNDLE_ID}')
print(f'Name: {APP_NAME}')
print(f'SKU: {SKU}')
except urllib.error.HTTPError as e:
body = e.read().decode()
if e.code == 401:
print('ERROR: Session expired. Call asc_web_auth MCP tool to re-authenticate.')
elif e.code == 409:
print(f'ERROR: App may already exist or conflict. Details: {body[:500]}')
else:
print(f'ERROR creating app: HTTP {e.code} — {body[:500]}')
sys.exit(1)
"
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.
- 1mo ago First seen · 173 lines · 19 tokens per session scan A 0dc0b9ff6faf
asc-app-create-ui is a skill published in the GitHub repository blitzdotdev/blitz-mac (1,761 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,576 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
app-rejection-recovery
When the user's app or update was rejected by Apple App Review or Google Play Review and they need to diagnose why, fix it, and resubmit fast. Use when the user mentions "app rejected", "App Review rejection", "guideline violation", "Apple rejected my app", "Google Play rejected", "Play policy violation", "Resolution…
android-aso
When the user wants to optimize their Google Play Store listing — title, short description, full description, keywords, ratings, or Play Store-specific features. Use when the user mentions "Google Play", "Android", "Play Store", "Play Console", "short description", "full description indexed", "Google Play ASO", or…
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…
attribution-setup
When the user wants to set up, debug, or interpret app install attribution — including SKAdNetwork (SKAN), Apple's AdAttributionKit, Google Play Install Referrer, MMPs (AppsFlyer, Adjust, Singular, Branch, Kochava), deep links, deferred deep links, conversion values, postback windows, or privacy thresholds. Use when…
custom-product-pages
When the user wants to design, deploy, or measure Apple Custom Product Pages (CPP) — the alternate App Store product pages with different screenshots, preview videos, and promo text shown to users coming from specific URLs (typically ad campaigns or social posts). Use when the user mentions "Custom Product Page"…
web-to-app-funnel
When the user wants to design or optimize the funnel that takes web visitors into installing and onboarding the app — including smart app banners, web-to-app deep links, deferred deep links, web onboarding (Stripe-paid web flow before app install), QR codes, "open in app" CTAs, and the trade-off between paying on web…