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 AnilBurcu/claude-code-react-native --skill prep-releasegit clone --depth 1 https://github.com/AnilBurcu/claude-code-react-nativeWrote 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/anilburcu/claude-code-react-native/prep-release)<a href="https://agentmods.dev/skills/anilburcu/claude-code-react-native/prep-release"><img src="https://agentmods.dev/badge/skills/anilburcu/claude-code-react-native/prep-release/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/anilburcu/claude-code-react-native/prep-release"><img src="https://agentmods.dev/badge/skills/anilburcu/claude-code-react-native/prep-release.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 | $0.00040 | $0.00559 |
| Opus 5.5 | $0.00016 | $0.00224 |
| Sonnet 5.5 | $0.00008 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
prep-release 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 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.
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.
What it actually says
Run a pre-release audit for $ARGUMENTS (default: both platforms). Verify in the actual project files; never assume. Output a pass/fail table with evidence, so the user can fix failures and rerun.
Check, with the eas-release skill as the rulebook:
- Versioning: user-facing version bumped since the last release tag; build numbers set to auto-increment or manually bumped; git tag plan stated.
- OTA fence: runtime version policy present; if any native dependency or config plugin changed since the last store build, flag that this release MUST be a store build and OTA publishing to old channels is forbidden until it ships.
- Permissions honesty: cross-check declared permissions and usage strings (Info.plist keys, Android permissions) against what the code actually imports. Camera/mic/location/notification strings present where used, and no leftover permissions from removed features, which reviewers flag.
- Secrets scan: grep the source and app config for things that must not ship: private API keys, service-role or server keys, live payment secrets, hardcoded backend admin URLs. Public/publishable keys are fine; call out anything ambiguous.
- Store hygiene: account deletion path exists if accounts exist; restore purchases reachable if IAP exists; sign-in options meet platform rules; privacy labels and data safety answers match the SDK list (list the SDKs that collect data so the user can compare).
- Config sanity: production build profile points at production backend; no debug flags, staging URLs or test paywalls behind release config; app icon and splash present for both platforms.
- Quality gates: typecheck, lint and tests pass; if there is a preview/QA build lane, confirm the release candidate went through it.
- Android native alignment: when a build artifact is at hand, verify 16 KB page alignment of native libraries (
zipalign -c -P 16 -v 4on an APK built from the bundle); Play rejects unaligned.sofiles for apps targeting Android 15+. Without an artifact, list native dependencies whose last release predates the requirement as warnings.
Rules of engagement: read-only plus running the project's own check commands. Findings come back as blocker vs warning, each with file evidence. End with a plain verdict: ready to submit, or the ordered list of what blocks it.
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 Changed · +1 lines f8515926ef75
- 1mo ago First seen · 21 lines · 40 tokens per session scan A e38320d20495
prep-release is a skill published in the GitHub repository AnilBurcu/claude-code-react-native (3 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 559 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 2026-08-31.
Other skills, from other repositories
apple-release-ops
The mechanics of shipping Apple apps. Use for ANY code signing error ("no signing certificate", "provisioning profile doesn't include...", "revoked certificate"), provisioning profiles, certificates, entitlements, capabilities, TestFlight (groups, expiry, feedback), App Store Connect, uploading builds, xcodebuild…
expo-56
Authoritative, version-pinned reference for Expo SDK 56 and SDK 57 — both postdate your training, so defer to this skill over memory for anything Expo. SDK 57 is the current release (2026-07-08, React Native 0.86); SDK 56 is the previous, still-supported release (React Native 0.85). Use it whenever the user is…
ios-app-store-submission
Build and submit iOS apps to App Store Connect using fastlane (match/gym/pilot/deliver) or EAS (eas build / eas submit) for native (Swift/SwiftUI/UIKit), React Native, Expo, Flutter, and Capacitor projects. Use when archiving to .xcarchive, validating, uploading to TestFlight, configuring code signing and…
submitting-app-release
Runs pre-flight validation gates and submits the app to App Store Connect and Google Play Console via EAS CLI. Use when the user says "release", "submit to store", "publish", "deploy app", or "submit for review". Always runs release-checklist.js first — never submits past a failing gate without explicit user…
managing-app-versions
Manages semantic versioning for mobile apps across iOS and Android platforms. Use when the user says "bump version", "increment build number", "set version to", "release patch/minor/major", or "sync build numbers". Single source of truth is .msd/versions/{app-id}/version.json. Syncs to app.json (Expo), Info.plist…
axiom-shipping
Use when preparing an app for App Store submission, handling rejections or appeals, managing App Store Connect and Xcode Cloud, or triaging TestFlight/Sentry crash corpora. Covers checklists, metadata, privacy manifests, age ratings, export compliance.