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/sharko99/relay/claude-mdgit clone --depth 1 https://github.com/sharko99/relayWrote 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/sharko99/relay/claude-md)<a href="https://agentmods.dev/instructions/sharko99/relay/claude-md"><img src="https://agentmods.dev/badge/instructions/sharko99/relay/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 | $0.04335 | $0.04335 |
| Opus 5 | $0.02167 | $0.02167 |
| Sonnet 5 | $0.00867 | $0.00867 |
| Haiku 4.5 | $0.00434 | $0.00434 |
Grade A, and why
relay CLAUDE.md scanned grade A 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl > internal step. New copyable things get a kind here, not an ad-hoc How it starts
The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Relay — project instructions
Relay is a keyboard-first, file-based API client (Tauri 2 + React 19). The
workspace is plain YAML on disk (~/Relay); the Rust core owns execution,
storage, and secrets, the frontend owns editing.
Repository map
apps/desktop— the app.src/is the React frontend (features/,stores/,design-system/,ipc/),src-tauri/the Rust core.public/llms.txtis the workspace guide deployed to users (system 11).scripts/holds the render harnesses:pnpm promo(marketing shots topromo/),pnpm banners(docs page banners toapps/docs/src/assets).apps/docs— the documentation site (Astro 5 + MDX). See "Documentation surfaces" below.docs/— contributor docs:ARCHITECTURE.md,CONTRIBUTING.md, anddesign/notes (undo, auth, export-code, mcp-server) that record why the larger systems are shaped the way they are. Read the relevant one before reworking such a system; add one when you build something of that size.
Architecture ground rules
- The frontend never touches the network or the filesystem. All I/O crosses a
#[tauri::command]insrc-tauri/src/ipc; the typed bindings are generated (system 9). If a feature needs a new capability, it gets a command, not a webview workaround. - Vault secrets live Rust-side only. This is system 8 and it is the one rule with zero exceptions beyond the single sanctioned Reveal path.
- The files on disk are the source of truth, and users edit them outside the app ("Open in VS Code" is a feature). Never assume the app is the only writer: verify before overwriting, reload on external change.
Cross-cutting systems — enroll every new feature
Relay's quality comes from a handful of cross-cutting systems. When adding or changing a feature, walk this list and enroll the feature in each system that applies. A feature that skips one (a menu without file actions, a mutation the undo stack can't see, a selectable thing outside the focus system) degrades the whole app, not just itself.
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.
- 4d ago First seen · 306 lines · 4,335 tokens per session scan A 07f39fd0a439
relay CLAUDE.md is an instructions file published in the GitHub repository sharko99/relay (0 stars, last pushed 1mo ago), licensed MIT. It adds 4,335 tokens to every session, about $0.0217 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.