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 Lykhoyda/rn-dev-agent --skill rn-feature-developmentgit clone --depth 1 https://github.com/Lykhoyda/rn-dev-agentWrote 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/lykhoyda/rn-dev-agent/rn-feature-development)<a href="https://agentmods.dev/skills/lykhoyda/rn-dev-agent/rn-feature-development"><img src="https://agentmods.dev/badge/skills/lykhoyda/rn-dev-agent/rn-feature-development/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/lykhoyda/rn-dev-agent/rn-feature-development"><img src="https://agentmods.dev/badge/skills/lykhoyda/rn-dev-agent/rn-feature-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 205 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 521 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00086 | $0.06607 |
| Opus 5.5 | $0.00034 | $0.02643 |
| Sonnet 5.5 | $0.00017 | $0.01321 |
| Haiku 4.5 | $0.00009 | $0.00661 |
Grade A, and why
rn-feature-development 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 29d 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 — 574 lines — stays where its author put it; the contents beside it link to each section on GitHub.
React Native Feature Development (8-Phase Pipeline)
For package helpers, resolve <package-root> as ../.. from this exact
SKILL.md; never scan Codex caches or assume the user's workspace contains
rn-dev-agent maintenance scripts.
You are helping a developer implement a new feature in a React Native app. Follow this systematic approach: understand the codebase deeply, ask about all ambiguities, design an elegant architecture, implement, verify live on the simulator, review quality, and produce E2E proof with screenshots.
Core Principles
- NEVER skip phases: Every phase (1-8) must be executed. Do NOT bypass explorer agents (Phase 2), architect agents (Phase 4), reviewer agents (Phase 6), or proof capture (Phase 8) even when the codebase is familiar. Speed comes from parallel agent launches, not phase elimination.
- Ask clarifying questions: Identify all ambiguities and edge cases before implementing. Wait for user answers before proceeding.
- Understand before acting: Read and comprehend existing code patterns first.
- Read files identified by agents: When launching agents, ask them to return lists of important files. After agents complete, read those files yourself.
- Simple and elegant: Prioritize readable, maintainable code.
- Use TodoWrite: Track all progress through the phases.
- Verify on device: After implementation, prove it works with a live screenshot and CDP state checks.
- Cross-platform visual verification: When both iOS and Android are available, compare screenshots element-by-element. A screen that renders without crashing but has missing icons/images is a FAIL, not a PASS.
- Evaluator hook: if
dev/evaluator.mdexists in the plugin root, log every phase's events per its matching Phase section there (it defines what each phase records; re-verification logs as Phase 5.5-retry); Phase 7 finalizes the report and opens or updates GitHub Issues for high-confidence bugs.
Phase 1: Discovery
What ships with it
1 file 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.
- 29d ago Changed · +7 lines 00483aa44684
- 1mo ago Changed f201a8742dd7
- 1mo ago First seen · 567 lines · 86 tokens per session scan A 520bff5e394f
rn-feature-development is a skill published in the GitHub repository Lykhoyda/rn-dev-agent (20 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 6,607 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
skill-packager
Authors Agent Skills v1.0 packages (SKILL.md plus references/scripts), runs packageskill to produce a standards-compliant zip, and uses installskill to add skills from HTTPS, registry, workspace, or an uploaded archive. Use when the user wants to turn documentation, workflows, or code into a portable skill, export a…
workflow-helper
Guidance for creating, managing and executing workflow automations that chain multiple tools and agents together. Use when the user asks about building, listing, running or composing workflows and automated task pipelines.
data-analyzer
Guidance for analyzing structured data, generating statistics and producing data-driven insights. Use when the user asks to analyze data, compute statistics, find patterns, or generate analytical reports.
document-processor
Guidance for processing documents, extracting content, and transforming structured information. Use when the user asks to process, parse, extract, or transform document content such as PDFs, Word files, or spreadsheets.
attendance-signin-sheet
A spreadsheet generator for printable attendance or meeting sign-in sheets. It turns a list of names into rows with columns such as signatures, dates, departments, or employee IDs.
travel-expense-audit
A travel-expense review workflow that checks reimbursement claims against policy handbooks and rate tables. It covers items such as hotel, transport, and daily meal allowances.