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 cmdr-chara/codex-toolkit --skill expo-react-native-buildergit clone --depth 1 https://github.com/cmdr-chara/codex-toolkitWrote 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/cmdr-chara/codex-toolkit/expo-react-native-builder)<a href="https://agentmods.dev/skills/cmdr-chara/codex-toolkit/expo-react-native-builder"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/expo-react-native-builder/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/cmdr-chara/codex-toolkit/expo-react-native-builder"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/expo-react-native-builder.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 | $0.00039 | $0.00772 |
| Opus 5.5 | $0.00016 | $0.00309 |
| Sonnet 5.5 | $0.00008 | $0.00154 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
expo-react-native-builder 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 24d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expo React Native Builder
Build production Expo/React Native behavior from repository constraints rather than from a default package list.
Trigger boundary
Use this skill for:
- implementing or auditing an existing Expo/React Native app;
- Expo Router, development builds, native modules, offline/data behavior, EAS Build/Update, device integration, or store delivery.
Do not trigger when the mobile platform is unresolved; use mobile-architecture-director. A version/SDK migration whose central problem is compatibility belongs to codebase-evolution-controller.
Required inputs
Resolve repository state, Expo/RN/React/Node/package-manager constraints, app config and native/prebuild ownership, product flows, backend/device contracts, offline requirements, accessibility/localization, EAS profiles, release targets, and protected user work.
For a quick read-only inventory, run:
python skills/expo-react-native-builder/scripts/expo_project_inventory.py . --format markdown
Treat its output as signals to verify, not semantic truth.
Safety baseline
- Preserve uncommitted work and repository conventions.
- Prefer built-in Expo/RN capabilities or an existing repository package when sufficient.
- Do not silently add dependencies, regenerate native projects, change signing, publish updates, or submit stores.
- Keep secrets out of client bundles and logs.
- Expo Go is not production release evidence when custom native behavior or production configuration matters.
Workflow
- Establish ownership. Map routing, app lifecycle, native directories/prebuild policy, development builds, backend/data boundaries, and release/update configuration.
- Model behavior. Define loading, empty, error, retry, offline/stale, auth, permission, background, interruption, and process-restart states before choosing libraries.
- Choose dependencies conditionally. Do not start with a package list. Check existing/built-in capability first; for new packages verify compatibility, maintenance, license, security/deprecation, runtime/build cost, and removal path. Use
references/expo-react-native-ecosystem-2026-07-17.mdwhen package selection matters. - Implement boundaries. Keep navigation, server state, durable local state, forms, device APIs, and native modules owned by the layer that can enforce their lifecycle and trust requirements.
- Handle offline/update risk. Read
references/offline-updates-and-security.mdfor durable queues, conflict/idempotency, storage, update compatibility, and sensitive data. - Verify the feature. Use focused unit/integration tests plus representative device/emulator checks for native, permission, background, deep-link, accessibility, and performance behavior that cannot be proven in JS alone.
- Prepare release. Read
references/release-checklist.mdonly for build/update/store work. Native dependency, config, permission, or entitlement changes require a compatible binary rather than a JS-only update.
What ships with it
5 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.
- 24d ago Changed · -152 lines · -53 tokens per session 1560379a9e7a
- 1mo ago First seen · 211 lines · 92 tokens per session scan A cbaa46d31f99
expo-react-native-builder is a skill published in the GitHub repository cmdr-chara/codex-toolkit (2 stars, last pushed 11d ago), licensed MIT. It adds 39 tokens to every session and 772 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
trace
Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
establishing-code-ownership
Determine which PostHog team owns a file, directory, or code path, or enumerate all code a team owns (via distributed owners.yaml, products//product.yaml, and .github/CODEOWNERS). Use when assigning a reviewer, attributing a bug or slow query to a team, routing work, scoping a team-wide audit, or answering "who owns…
extending-hobby-smoke-tests
Design, extend, review, or debug PostHog Hobby end-to-end smoke tests in bin/hobby-ci.py and .github/workflows/ci-hobby.yml. Use when adding an ingestion round trip, deciding whether a product belongs in Hobby CI, changing the CI Hobby service topology or API-key scopes, or diagnosing a smoke test that captures data…
react-doctor
Diagnose and fix React codebase health issues. Use when reviewing React code, fixing performance problems, auditing security, or improving code quality.
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.