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 agentmods add instructions/lykhoyda/rn-dev-agent/agents-mdgit clone --depth 1 https://github.com/Lykhoyda/rn-dev-agentWhat 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 | $0.05241 | $0.05241 |
| Opus 5 | $0.02620 | $0.02620 |
| Sonnet 5 | $0.01048 | $0.01048 |
| Haiku 4.5 | $0.00524 | $0.00524 |
Grade A, and why
rn-dev-agent AGENTS.md 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 yesterday.
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 — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guide For Agents
This file is for coding agents working in this repository. Keep it current and practical. Do not paste session memory, issue histories, or one-off debugging notes here.
Repository Map
- Root workspace: Yarn 4 workspace, managed by
package.jsonandyarn.lock. Usecorepack yarn ...from the repository root. packages/rn-dev-agent-core/: TypeScript MCP server, CDP bridge, device tools, learned actions, observability server.dist/is generated byyarn build/yarn build:weband is not committed.packages/claude-plugin/: Claude Code host package. Owns Claude manifests, hooks, commands, agents, skills, templates, helper scripts, packaged native runners, runner manifest, and bundled core runtime.packages/codex-plugin/: Codex host package. Owns.codex-plugin/,.mcp.json,bin/cdp-supervisor.js, commands, agents, skills, templates, packaged native runners, runner manifest, and bundled core runtime. Codex does not consume Claude hooks; "No plugin hooks" is expected.packages/shared-agent-knowledge/: canonical host-neutral workflow knowledge for skills, commands, agents, andtemplates/rn-agent/.packages/rn-fast-runner/: source iOS XCTest native runner.packages/rn-android-runner/: source Android UiAutomator native runner.apps/docs-site/: deliverable documentation site workspace.- Engineering processes, plans, stories/specifications, audits, diagnostics,
comparisons, competitor analyses, and general research live in the workspace
docs/; never add a top-leveldocs/tree here. Captain-approved architecture records belong in Anton Factoryarchitect-docs; link to either owner instead of copying.
The plugin repo ships user-visible code and docs. Internal proof artifacts, bench reports, and project planning belong in GitHub Issues, PRs, or the sibling workspace only when explicitly requested.
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.
- yesterday First seen · 377 lines · 5,241 tokens per session scan A ae2043316914
rn-dev-agent AGENTS.md is an instructions file published in the GitHub repository Lykhoyda/rn-dev-agent (11 stars, last pushed yesterday), licensed MIT. It adds 5,241 tokens to every session, about $0.0262 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 2026-08-30.
Other instructions, from other repositories
LeAgent AGENTS.md
Instructions for vixues/LeAgent, covering leagent development guidelines, project overview, architecture, execution topology (one kernel, many ingresses) and surface map (where things live).
pi-agent-dashboard CLAUDE.md
Instructions for BlackBeltTechnology/pi-agent-dashboard, a project described as: Real-time web dashboard for pi coding-agent sessions. Multi-session view, live chat mirroring, integrated terminal, diff viewer, pi-flows execution, and mobile-first remote control via mDNS or zrok tunnel. Coexists with pi's TUI — doesn't…
clarion CLAUDE.md
Claude Code instructions for celanthe/clarion, covering clarion — agent voice manager, what it does, architecture, running it and ui only (edge tts, zero config).
upwork-agent CLAUDE.md
Claude Code instructions for citizenweb3/upwork-agent, covering upwork agent, setup (for a new machine), prerequisites, step 1: install dependencies and step 2: configure environment.
optillm CLAUDE.md
Instructions for algorithmicsuperintelligence/optillm, covering claude.md, project overview, core architecture, main components and development commands.
thinkrail AGENTS.md
Instructions for JetBrains/thinkrail, covering thinkrail, module structure & boundaries (top-priority requirement), engine: pi only, in-process, architecture (three rings) and repo layout.