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 tjdrhs90/rn-launch-harness --skill rn-harness-specgit clone --depth 1 https://github.com/tjdrhs90/rn-launch-harnessWrote 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/tjdrhs90/rn-launch-harness/rn-harness-spec)<a href="https://agentmods.dev/skills/tjdrhs90/rn-launch-harness/rn-harness-spec"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-spec/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/tjdrhs90/rn-launch-harness/rn-harness-spec"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.01597 |
| Opus 5 | $0.00015 | $0.00798 |
| Sonnet 5 | $0.00006 | $0.00319 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
rn-harness-spec 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 11d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rn-harness-spec — Phase 2.5: Spec Planning
Breaks down the PRD into file-level task checklists under docs/specs/, organized by feature and implementation phase. Sits between Plan (Phase 2) and Design (Phase 3).
Trigger
Called by the orchestrator after Phase 2 (Plan) completes.
Input
docs/harness/plans/YYYY-MM-DD-prd.md(PRD from Phase 2)docs/harness/config.md
Process
Step 1: Extract Feature List
Read the PRD and extract the full list of features to implement. Map each feature to the FSD module structure defined in the PRD (features/, entities/, widgets/, shared/).
Sort features by priority:
- P0 features first (MVP required)
- P1 features next (important)
- P2 features last (future roadmap)
Step 2: Create Feature Spec Directories
For each feature, create a numbered directory under docs/specs/:
docs/specs/
├── 01-auth/
├── 02-home/
├── 03-profile/
├── ...
└── README.md
The NN prefix reflects implementation priority order (01, 02, 03...).
Step 3: Generate Phase Files
Inside each feature directory, create phase markdown files:
docs/specs/01-auth/
├── phase1-mvp.md # Core MVP functionality
├── phase2-enhancement.md # Enhancements and extensions
└── phase3-polish.md # Optimization and polish (if needed)
Phase breakdown rules:
- Phase 1 (MVP): Minimum viable implementation — types, API, store, core UI, screen, barrel export
- Phase 2 (Enhancement): Extended features — validation, error states, loading states, edge cases
- Phase 3 (Polish): Optimization — animations, accessibility, performance tuning
P0 features should have at least Phase 1 and Phase 2. P1 features may only have Phase 1. P2 features are documented but not given phase files (noted in README as future scope).
Step 4: Write Tasks in Checkbox Format
Each phase file must follow this exact structure:
---
feature: auth
phase: 1
title: MVP - Authentication
status: not-started
created: YYYY-MM-DD
updated: YYYY-MM-DD
---
# Phase 1: MVP - Authentication
## Tasks
### Entity Setup
- [ ] `src/entities/user/types/index.ts` — IUser interface definition
- [ ] `src/entities/user/store/index.ts` — Zustand user store
### Feature Implementation
- [ ] `src/features/auth/api/auth.api.ts` — Login/signup API calls
- [ ] `src/features/auth/hooks/useLogin.ts` — Login mutation hook
- [ ] `src/features/auth/hooks/useRegister.ts` — Signup mutation hook
- [ ] `src/features/auth/store/index.ts` — Token management store
- [ ] `src/features/auth/ui/LoginForm.tsx` — Login form component
- [ ] `src/features/auth/types/index.ts` — Auth-related types
- [ ] `src/features/auth/index.ts` — Barrel export
### Screen Implementation
- [ ] `app/(auth)/login.tsx` — Login screen
- [ ] `app/(auth)/register.tsx` — Register screen
### QA
- [ ] typecheck passes
- [ ] lint passes
- [ ] feature functions correctly
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.
- 11d ago First seen · 214 lines · 29 tokens per session scan A c6c160b0795d
rn-harness-spec is a skill published in the GitHub repository tjdrhs90/rn-launch-harness (9 stars, last pushed 9d ago), licensed MIT. It adds 29 tokens to every session and 1,597 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
appstore-publish
A workflow guide for publishing an app to the App Store, including prerequisites, tool loading, submission, and resubmission steps.
mimi-seed-update
An update guide for Mimi Seed that identifies the installed version and installation type, then applies the matching update process. It also covers plugin installation.
playstore-publish
A guide for publishing to Google Play, including required conditions, tool loading, the run sequence, in-app products, and subscriptions. Google Play is Google’s store for Android apps and digital purchases.
video-create-publish
Create, render, validate, and optionally publish polished short-form videos and YouTube Shorts with Mimi Seed. Use for story-to-video production, vertical social videos, carousel-to-video adaptations, visual-quality revisions, or YouTube upload/status work where typography, shorts-style burned captions, human-safe…
mimi-seed-onboarding
An onboarding guide for Mimi Seed that checks installation status, scans connections, shows what it can do, and identifies the minimum credentials needed for a goal. Credentials are login details or access keys.
mimi-seed
A guide for using Mimi Seed, including required conditions, loading its tools, the execution flow, and linking local login details to a remote MCP service. MCP is a way for an agent to use tools provided by another program or service.