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 rshankras/claude-code-apple-skills --skill ad-attributiongit clone --depth 1 https://github.com/rshankras/claude-code-apple-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/rshankras/claude-code-apple-skills/ad-attribution)<a href="https://agentmods.dev/skills/rshankras/claude-code-apple-skills/ad-attribution"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/ad-attribution/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/rshankras/claude-code-apple-skills/ad-attribution"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/ad-attribution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 66 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 74 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.
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 | $0.00070 | $0.01430 |
| Opus 5 | $0.00035 | $0.00715 |
| Sonnet 5 | $0.00014 | $0.00286 |
| Haiku 4.5 | $0.00007 | $0.00143 |
Grade A, and why
ad-attribution 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Attribution (AdAttributionKit)
You can't optimize paid traffic you can't measure. AdAttributionKit is Apple's privacy-preserving attribution framework — interoperable with SKAdNetwork, and the go-forward path (it also works in alternative marketplaces). This skill covers the advertised-app side: what an indie running paid campaigns must implement and how to design conversion signals that survive privacy thresholds.
Note the seam: Apple Ads attribution uses the AdServices framework, not AdAttributionKit —
campaigns there are measured in the Apple Ads console (see app-store/apple-search-ads). This
skill is for every other paid channel (ad networks, social, publishers).
When This Skill Activates
- Running or planning paid user acquisition outside Apple Ads
- "How do I know which campaign drove installs?" / measuring re-engagement ads
- Designing or debugging conversion values / postbacks
- Migrating from SKAdNetwork (fully interoperable — registered networks need no re-enrollment)
How it works (the 60-second model)
Ad network signs an ad (compact JWS impression) → publisher app shows it → user installs (or re-engages) → after a privacy-delayed measurement window, a postback with your conversion info goes to the ad network (and optionally to you). Attribution requires no user tracking; the price is coarser data, governed by crowd anonymity.
Conversion-value strategy (the part that's actually yours)
- Two granularities: fine value 0–63 and coarse low/medium/high. Low crowd sizes
downgrade fine → coarse and can trim the 4-digit campaign
source-identifierto as few as its first 2 digits — so encode what matters most (campaign family, geo tier) in the first two digits, detail in the rest. - Map values to revenue-predictive early behavior (completed onboarding, trial start, first purchase), not vanity events. 64 slots go fast; reserve ranges (e.g. 0–15 activation, 16–47 monetization ladder, 48–63 reserved).
- Update with
updateConversionValue(_:)/PostbackUpdate; setlockPostbackwhen the value is final to schedule transmission (still privacy-delayed, never instant). - Re-engagement postbacks are separate from install postbacks: update them independently via
conversionTypes(.install / .reengagement); the first re-engagement update must land within 48 hours. - Multiple simultaneous re-engagement campaigns need conversion tags (iOS 18.4+): read the
tag from the re-engagement URL's query items, store it, and pass it in
PostbackUpdate— without a tag, updates hit only the most recent conversion.
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.
- 10d ago First seen · 103 lines · 70 tokens per session scan A fa4c02a9ce66
ad-attribution is a skill published in the GitHub repository rshankras/claude-code-apple-skills (713 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,430 once invoked, about $0.0003 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.
Other skills, from other repositories
thinking-theory-of-constraints
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.
electron-desktop
Desktop application development with Electron for Windows, macOS, and Linux. Use when building cross-platform desktop apps, implementing native OS features, or packaging web apps for desktop.
impact-report-writer
Nonprofit/NGO impact report generation with data visualization suggestions, outcome metrics, narrative structure, and program data presentation. Use when writing impact reports, annual reports, or program evaluation summaries.
investment-memo-generator
Investment memo creation combining financial analysis, document generation, and structured templates. Use when creating investment memos, pitch decks, deal summaries, or investment committee materials.
generic-static-feature-developer
Guide feature development for static HTML/CSS/JS sites. Covers patterns, automation workflows, and content validation. Use when adding features, modifying automation, or planning changes.
python-memory-safe-scripts
Memory-safe Python script patterns for long-running processes under systemd MemoryMax constraints. Covers allocator purge (mimalloc/glibc malloctrim), HTTP response lifecycle, DataFrame cleanup, thread-local connection reuse, and periodic GC cadence. Battle-tested through 5 OOM optimization cycles on production GPU…