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/edwardathomson/llm-remote-runner/claude-mdgit clone --depth 1 https://github.com/EdwardAThomson/LLM-Remote-RunnerWrote 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/instructions/edwardathomson/llm-remote-runner/claude-md)<a href="https://agentmods.dev/instructions/edwardathomson/llm-remote-runner/claude-md"><img src="https://agentmods.dev/badge/instructions/edwardathomson/llm-remote-runner/claude-md.svg" alt="Measured on agentmods" 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 | $0.01986 | $0.01986 |
| Opus 5 | $0.00993 | $0.00993 |
| Sonnet 5 | $0.00397 | $0.00397 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade A, and why
LLM-Remote-Runner CLAUDE.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 5d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Monorepo layout
pnpm workspace with four packages — see pnpm-workspace.yaml:
gateway/(@codex/gateway) — NestJS API, the only package with non-trivial logic.sdk/(@codex/sdk) — Shared types + fetch/SSE client wrappers consumed byweband external scripts.web/(@codex/web) — Vite + React 18 + React Router v7 SPA. No Next.js, no App Router; routes live inweb/src/App.tsx, components inweb/components/. The web app readsVITE_GATEWAY_URLfromweb/.env.local(viaimport.meta.env); the legacyNEXT_PUBLIC_GATEWAY_URL/NEXT_PUBLIC_AUTH_TOKENnames are no longer read by any code — if you see them in a local.env.local, they silently do nothing.mobile/(@codex/mobile) — Expo scaffold, mostly experimental.
Commands
Run from repo root unless noted. Install with pnpm install --recursive (requires corepack enable pnpm).
| Task | Command |
|---|---|
| Gateway dev (hot reload, port 3000) | pnpm --filter @codex/gateway dev |
| Web dev (Vite, port 3001) | pnpm --filter @codex/web dev |
| Build everything | pnpm build (root) or pnpm -r run build |
| Gateway tests (Jest) | pnpm --filter @codex/gateway test |
| Single Jest test by name | pnpm --filter @codex/gateway test -- -t "partial test name" |
| Single Jest spec file | pnpm --filter @codex/gateway test -- path/to/file.spec.ts |
| Web typecheck | pnpm --filter @codex/web typecheck |
| Initial auth setup | cd gateway && pnpm tsx scripts/setup-auth.ts then rm scripts/setup-auth.ts |
Repair broken claude CLI install |
./scripts/fix-claude.sh |
OpenAPI / Swagger UI is at http://localhost:3000/api/docs once the gateway is up (JSON at /api/docs/json).
Gateway architecture
NestJS modules wired in gateway/src/app.module.ts. Global JwtAuthGuard + PrincipalThrottlerGuard apply to every route unless decorated @Public().
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.
- 5d ago First seen · 104 lines · 1,986 tokens per session scan A 5002b6126812
LLM-Remote-Runner CLAUDE.md is an instructions file published in the GitHub repository EdwardAThomson/LLM-Remote-Runner (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,986 tokens to every session, about $0.0099 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 instructions, from other repositories
agent-session-parser AGENTS.md
AGENTS.md instructions for BobDLA/agent-session-parser, covering agents.md, 项目定位, 先读这些文档, 当前边界 and 开发方式.
AionUi AGENTS.md
AGENTS.md instructions for iOfficeAI/AionUi, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.
obsidian-mind CLAUDE.md
Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.
obsidian-mind AGENTS.md
AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.
parallel-code CLAUDE.md
Claude Code instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.
ox AGENTS.md
AGENTS.md instructions for sageox/ox, covering human attention is the scarcest resource, what is ox?, quick start, terminology and required reviews.