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 agentmods add skills/sungurerdim/dev-skills/ds-launchnpx skills add sungurerdim/dev-skills --skill ds-launchgit clone --depth 1 https://github.com/sungurerdim/dev-skillsWrote 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/sungurerdim/dev-skills/ds-launch)<a href="https://agentmods.dev/skills/sungurerdim/dev-skills/ds-launch"><img src="https://agentmods.dev/badge/skills/sungurerdim/dev-skills/ds-launch.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00033 | $0.06006 |
| Opus 5 | $0.00016 | $0.03003 |
| Sonnet 5 | $0.00007 | $0.01201 |
| Haiku 4.5 | $0.00003 | $0.00601 |
Grade A, and why
ds-launch 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.
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.
How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ds-launch
~40% of iOS submissions get delayed or rejected for preventable errors. This skill scans your project and flags them before you submit.
Store & Release Management — Store submission, listing optimization, release strategy, and post-launch monitoring.
Completion Evidence — applies to every phase: Report
done/OKonly with the machine-checkable evidence the gates name — the exact command run and its observed output (orfile:linediff). Missing evidence → reportINCOMPLETEplus what is missing. Self-assessment is never evidence. (This band repeats at file end by design — both copies are normative.)
Triggers
- User runs
/ds-launch, asks to submit to app store, prepare for launch, or manage releases — or about store listing, screenshots, privacy labels, release notes, "how do I publish my app"
Triggers — INVOKE / DON'T INVOKE
| INVOKE | DON'T INVOKE |
|---|---|
| "submit to App Store / Play Store / Mac App Store" | "deploy backend to VPS / container" (→ ds-deploy) |
| "App Store privacy labels (store-correctness check)" | "full GDPR/KVKK privacy compliance" (→ ds-compliance --privacy) |
| "author a perf budget (LCP/INP/p99/bundle) + wire CI enforcement" | "fix the performance regression itself" (→ ds-review / ds-fix) |
| "pre-review checklist (rejection prevention)" | "audit mobile app quality" (→ ds-mobile) |
Contract
Dimensions: A4, D1 (perf-budget), D6, A9 (conditional ecosystem rules)
- Covers store account setup, listing metadata, review preparation, release management; generates checklists + metadata — does NOT submit to stores directly.
- Minimal liability + maximum privacy + maximum automation: store-compliant metadata + common rejection flags; privacy labels with minimal data-collection focus; version management + release notes generation + staged rollout.
- Standalone. Uses blueprint profile when available;
ds/audit/findings.mdonly when fresh (git_hash == HEADAND current run-cycle); own analysis otherwise. - Full accounting enforced: every finding and planned check ends in an explicit disposition (fixed / skipped + reason / only you can do); summary totals balance.
- Pre-existing / out-of-scope errors detected during work are NOT skipped — fixed inline or escalated with concrete blocker.
- State-exempt: audit is regenerable; generated configs/fixes land in the working tree — git is the durable record.
- Metadata directory:
ds/launch/holds this skill's committed deliverables only — store listing text, privacy-label mappings, release notes,perf-budget.json, submission notes (submission-notes-{apple,google}.txt,submission-meta.yml). No other skill or scratch output writes there.
What ships with it
6 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.
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.
- yesterday Changed · -63 lines 94ff47f0c97a
- 4d ago First seen · 323 lines · 33 tokens per session scan A a862af380463
ds-launch is a skill published in the GitHub repository sungurerdim/dev-skills (1 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 6,006 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 2026-08-31.
Other skills, from other repositories
first-plan-lens-mobile
Stack lens para mobile - React Native, Swift (iOS), Kotlin (Android), Flutter. Use durante Discovery quando pubspec.yaml, Package.swift, build.gradle.kts (Android) ou react-native em deps for detectado. Cobre navegação, estado, módulos nativos, build/distribuição.
mobile-performance
Profile and audit mobile app performance -- cold/warm/hot startup time, memory leaks, battery drain, network efficiency, frame rate jank, and binary size. Triggers: diagnosing slow launches, investigating ANRs, reducing app size, or benchmarking rendering performance.
mobile-ux-patterns
Audit mobile UX implementation against platform conventions -- navigation patterns, gesture handling, pull-to-refresh, infinite scroll, skeleton screens, haptic feedback, adaptive layouts, deep linking, and accessibility..
app-size-optimizer
Analyzes mobile app binary size -- asset audit for unused images and font subsetting, code stripping with ProGuard and tree-shaking, on-demand resources, dynamic feature modules, and app thinning strategies..
mobile-analytics
Analyze mobile app analytics implementation including event tracking completeness and naming conventions, SDK configuration audit (Firebase Analytics, Amplitude, Mixpanel, PostHog), attribution tracking with AppsFlyer/Adjust/Branch and SKAdNetwork conversion values.
mobile-monetization
Audit mobile app revenue implementation -- in-app purchases, subscriptions, ad SDKs, paywall design, trial conversion funnels, and store billing compliance. Triggers: reviewing IAP flows, optimizing subscription conversion, checking ad mediation setup.