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 SummerRiversound/expo-launchpad --skill expo-launchpad-generatorgit clone --depth 1 https://github.com/SummerRiversound/expo-launchpadWrote 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/summerriversound/expo-launchpad/expo-launchpad-generator)<a href="https://agentmods.dev/skills/summerriversound/expo-launchpad/expo-launchpad-generator"><img src="https://agentmods.dev/badge/skills/summerriversound/expo-launchpad/expo-launchpad-generator/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/summerriversound/expo-launchpad/expo-launchpad-generator"><img src="https://agentmods.dev/badge/skills/summerriversound/expo-launchpad/expo-launchpad-generator.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 | $0.00085 | $0.09789 |
| Opus 5.5 | $0.00034 | $0.03916 |
| Sonnet 5.5 | $0.00017 | $0.01958 |
| Haiku 4.5 | $0.00009 | $0.00979 |
Grade C, and why
expo-launchpad-generator scanned grade C with 1 finding 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 23d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf app/(tabs) components/HelloWave.tsx components/ParallaxScrollView.tsx \ How it starts
The opening of the file, as written. The whole thing — 725 lines — stays where its author put it; the contents beside it link to each section on GitHub.
expo-launchpad-generator
Phase A, step 5 of the expo-launchpad pipeline. Builds the Expo (React Native + TypeScript) app or
game in three gated sub-phases (6a → 6b → 6c), branching every step by config.md's kind
(app | game). Each sub-phase ends with a HARD GATE (npx tsc --noEmit && npx expo lint && npx jest, all green) before the next sub-phase begins. On round N > 1, reads the previous evaluator
feedback and fixes only the listed failures.
All file schemas (config.md, state.md, contract.md, handoff/round-N-gen.md,
feedback/round-N-qa.md, the log tables) and the phase transition table are defined in
docs/harness-protocol.md — that document is the single source of truth (§2 for state.md
schema; §4 for handoff layout; §6 for log tables; §7 for the generator → evaluator transition).
Do not redefine schemas here. Every platform-robustness pattern (audio, haptics, lifecycle,
performance, persistence, accessibility, build/platform) is defined once in
docs/app-gotchas.md (R1–R11) — cite it; do not restate the patterns.
Round Handling and Feedback Intake
Workspace root
docs/harness/ is bootstrapped by the orchestrator in the directory the pipeline was invoked
from — call this the workspace root. It stays there for the entire pipeline and is never
moved or copied into the generated project. Before any other step (including the round-1/round-N
reads below), capture the workspace root once:
ROOT="$(pwd)"
From this point on, every harness file (config.md, state.md, contract.md, plans/*,
handoff/*, feedback/*, pipeline-log.md, build-log.md, screenshots/*) — whether read or
written via a Bash redirect, or read/written via the Write/Edit tools — uses the root-absolute
path "$ROOT/docs/harness/...", never a path relative to whatever directory the shell happens to
be in at the time. ROOT is fixed once, the same way <app_slug> and <N> are: treat it as a
value substituted verbatim into every command below, not a live shell variable that needs to
survive between separate tool invocations. This is what keeps --resume and the status/resume
skills working: they read docs/harness/state.md at a fixed path relative to the invocation
directory, forever.
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.
- 23d ago Changed · +9 lines 226c3ded1782
- 2mo ago First seen · 716 lines · 85 tokens per session scan C b45e4973c75f
expo-launchpad-generator is a skill published in the GitHub repository SummerRiversound/expo-launchpad (2 stars, last pushed 23d ago), licensed MIT. It adds 85 tokens to every session and 9,789 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
expo-launchpad-generator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| expo-launchpad-generatorSummerRiversound/expo-launchpad | Skill | 2 | 23d ago | MIT | C | 85 | Claude Code |
| mobile-developerdaffy0208/ai-dev-standards | Skill | 39 | 10mo ago | MIT | B | 16 | Claude Code, Codex |
| sceneviewsceneview/sceneview | Skill | 1.4k | yesterday | Apache-2.0 | A | 156 | Codex |
| sceneview-iossceneview/sceneview | Skill | 1.4k | yesterday | Apache-2.0 | A | 148 | Codex |
| compose-multiplatformericrisco/rsc-harness | Skill | 606 | yesterday | MIT | A | 80 | Claude Code, Codex |
| react-nativeericrisco/rsc-harness | Skill | 606 | yesterday | MIT | A | 90 | Claude Code, Codex |
| uniwinduni-stack/uniwind | Skill | 1.8k | yesterday | MIT | A | 130 | Claude Code, Codex |