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 tonone-ai/tonone --skill touch-auditgit clone --depth 1 https://github.com/tonone-ai/tononeWrote 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/tonone-ai/tonone/touch-audit)<a href="https://agentmods.dev/skills/tonone-ai/tonone/touch-audit"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/touch-audit/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/tonone-ai/tonone/touch-audit"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/touch-audit.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00047 | $0.01796 |
| Opus 5.5 | $0.00019 | $0.00718 |
| Sonnet 5.5 | $0.00009 | $0.00359 |
| Haiku 4.5 | $0.00005 | $0.00180 |
Grade A, and why
touch-audit 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 17d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Audit
You are Touch — the mobile engineer on the Engineering Team.
Steps
Step 0: Detect Environment
Scan the project to understand the mobile platform:
# iOS
ls -la *.xcodeproj *.xcworkspace 2>/dev/null
find . -name "Info.plist" -not -path "*/Pods/*" -not -path "*/build/*" 2>/dev/null | head -5
cat ios/Podfile 2>/dev/null | head -30
# Android
ls -la build.gradle* settings.gradle* 2>/dev/null
cat android/app/build.gradle 2>/dev/null | head -40
# React Native
cat package.json 2>/dev/null | grep -iE "react-native|expo"
# Flutter
cat pubspec.yaml 2>/dev/null
# Dependencies
cat Podfile.lock 2>/dev/null | wc -l
cat android/app/build.gradle 2>/dev/null | grep "implementation\|api(" | wc -l
cat package.json 2>/dev/null | grep -c ":" 2>/dev/null
cat pubspec.lock 2>/dev/null | grep "name:" | wc -l
# Crash reporting / analytics
grep -rl "Crashlytics\|Sentry\|BugSnag\|crashlytics\|sentry" --include="*.swift" --include="*.kt" --include="*.ts" --include="*.dart" --include="*.gradle" --include="Podfile" . 2>/dev/null | head -5
Note the platform, dependency count, and existing monitoring.
Step 1: App Size
Check for app size bloat:
- Total dependencies — count third-party libraries. More than 30 is a yellow flag
- Asset size — check for oversized images, bundled videos, uncompressed assets
- Unused dependencies — scan imports vs declared dependencies
- Binary size indicators — check build config for optimization flags
- Large frameworks — flag heavy SDKs (some analytics SDKs add 10MB+)
Benchmarks:
- Simple utility app: <30MB
- Standard app: <80MB
- Complex app: <150MB
- Anything over 200MB needs justification
Step 2: Startup Time
Audit cold start performance:
- Main thread work — check for synchronous initialization on app launch
- Lazy initialization — are heavy services initialized on first use or all at startup?
- Network calls on launch — any blocking network requests before showing UI?
- Database migrations — do they run on main thread during launch?
- Third-party SDK init — each SDK adds startup time (analytics, crash reporting, feature flags)
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.
- 17d ago First seen · 191 lines · 47 tokens per session scan A 7b975606fc18
touch-audit is a skill published in the GitHub repository tonone-ai/tonone (76 stars, last pushed 9d ago), licensed MIT. It adds 47 tokens to every session and 1,796 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-27.
Other skills, from other repositories
software-ios-runtime-debugging
Proves iOS build/install/launch truth and triages hangs, crashes, jank, memory kills, and stale builds. Use when simulator, bundle, or runtime performance state is in doubt.
software-android-runtime-debugging
Build/install/launch proof, ANR/jank/memory triage, and stale-build debugging for native Android apps. Use when runtime truth, performance, or crash root cause is in doubt.
verifying-external-behavior
Confirms what a third-party library, remote API, build backend, or scraped document actually does before writing code that depends on it — throwaway probes that run in seconds, permissive clients that forward wrong arguments instead of rejecting them, per-endpoint docs that don't generalize, response shapes that make…
sd-debug
The disciplined debug/fix loop the generic agent runs when a sd-verify / sd-test run FAILS (/foundry:sd-debug, software-delivery debug step, step 9). A PROCEDURE — reproduce → isolate → root-cause → minimal-fix → re-verify, ONE hypothesis per iteration (NOT shotgun edits), BOUNDED so it converges (the failure is fixed…
g-doctor
Read-only health diagnostics for G-Forge projects — 25 checks including hook registration, installed-copy drift, Check 23 plugin-version-lag, Check 24 CLAUDE.md injection-rule compliance, and Check 25 integration-tier guard. Recommends /plugins or /g-update by direction. Never writes.
g-optimize
Full-codebase or targeted performance audit. Detects algorithmic complexity problems, N+1 queries, re-render waste, resource leaks, and caching opportunities. Targeted scope produces an inline report. Whole-codebase scope produces a prioritised roadmap milestone.