agentmods.dev

protocol-launcher AGENTS.md

protocol-launcher AGENTS.md is an instructions file for Codex, OpenCode from zhensherlock/protocol-launcher. It costs 1,386 tokens per session, scanned A, original, MIT.

Project instructions for protocol-launcher, a pnpm workspace and Turbo monorepo—a repository containing several related packages and apps.

In plain words
What is it for?
Use it when developing the shared packages, URL generator library, documentation site, or promo-video app.
Why use it?
It explains the repository layout, important commands, build outputs, and rules for editing each part safely.

Instructions file for CodexOpenCode

not rated 127 7d ago A scan 1,386 tokens original MIT
View the source file zhensherlock/protocol-launcher
Install

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.

agentmods
npx agentmods add instructions/zhensherlock/protocol-launcher/agents-md
Clone the repo
git clone --depth 1 https://github.com/zhensherlock/protocol-launcher

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for protocol-launcher AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zhensherlock/protocol-launcher/agents-md.svg)](https://agentmods.dev/instructions/zhensherlock/protocol-launcher/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zhensherlock/protocol-launcher/agents-md"><img src="https://agentmods.dev/badge/instructions/zhensherlock/protocol-launcher/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,386 This file is loaded in full into every session.
When invoked 1,386 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01386 $0.01386
Opus 5 $0.00693 $0.00693
Sonnet 5 $0.00277 $0.00277
Haiku 4.5 $0.00139 $0.00139

Measured 5d ago against content hash 56a48ce02685, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

protocol-launcher 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 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.

AGENTS.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Protocol Launcher

Repo Shape

  • PNPM workspace + Turbo monorepo; main CI uses Node 22 and packageManager is [email protected] (npm-publish builds with Node 22, then publishes the packed tgz with Node 24).
  • Workspaces are packages/shared (qs, encodeUrlPayload), packages/protocol-launcher (published URL generator library), apps/docs (VitePress EN/ZH docs), and apps/promo-video (HyperFrames composition).
  • The root package and library package are both named protocol-launcher; use path filters like pnpm --filter ./packages/protocol-launcher build, not name filters.
  • Respect nested workspace instructions before editing package/app code: packages/shared/AGENTS.md, packages/protocol-launcher/AGENTS.md, apps/docs/AGENTS.md, and apps/promo-video/AGENTS.md.
  • Build outputs are ignored (dist, coverage, apps/docs/.vitepress/dist, apps/docs/.vitepress/cache, .turbo, apps/*/renders, apps/*/.thumbnails, apps/*/.waveform-cache); do not edit generated output.

Commands That Matter

  • Install: pnpm install.
  • Root dev loop: pnpm dev runs Turbo with --filter=./apps/*..., so docs, promo-video, and dependency package watchers start together. Use focused dev commands when you only need one app.
  • Focused dev: pnpm --filter ./apps/docs dev for VitePress, pnpm --filter ./apps/promo-video dev for HyperFrames preview.
  • CI-equivalent build/test: pnpm build then pnpm coverage; the build workflow runs both and deploys apps/docs/.vitepress/dist.
  • Root pnpm build only filters ./apps/docs...; promo video is separate via pnpm build:promo, pnpm check:promo, and pnpm render:promo.
  • Focused builds: pnpm --filter ./packages/shared build, pnpm --filter ./packages/protocol-launcher build, pnpm --filter ./apps/docs build.
  • Tests: pnpm test for all Vitest projects; focus with pnpm test packages/protocol-launcher/tests/vscode.test.ts, pnpm test vscode, or pnpm test -t "test name".
  • Coverage gate: pnpm coverage matches the build workflow's test step.
  • Formatting/linting: there is no root lint script; use npx biome check . or npx biome check --write .. Pre-commit only runs biome check --write on staged packages/**/*.{ts,js}.
  • Type checking: do not use bare npx tsc --noEmit from the root; there is no root tsconfig.json and tsconfig.root.json is the shared base. Use package builds or npx tsc -p packages/protocol-launcher/tsconfig.json --noEmit.

Read the full file on GitHub · 52 lines

Changes

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.

  1. 5d ago First seen · 52 lines · 1,386 tokens per session scan A 56a48ce02685

Subscribe to this mod's changes

protocol-launcher AGENTS.md is an instructions file published in the GitHub repository zhensherlock/protocol-launcher (127 stars, last pushed 7d ago), licensed MIT. It adds 1,386 tokens to every session, about $0.0069 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.

deep-linkdeeplinkesmprotocolquick-launcher
Related

Other instructions, from other repositories

AgentNetworkProtocol AGENTS.md

AGENTS.md instructions for agent-network-protocol/AgentNetworkProtocol, covering repository guidelines, project structure & module organization, protocol ownership boundary, build, test, and development commands and coding style & naming conventions.

agent-network-protocol/AgentNetworkProtocol · 763 tokens

Cotal AGENTS.md

AGENTS.md instructions for Cotal-AI/Cotal, covering agents.md, what this is, read these first, commands and repository map.

Cotal-AI/Cotal · 3,593 tokens

storagesdk AGENTS.md

Instructions for storagesdk/storagesdk, covering agents.md, what this is, locked design decisions, working principles and gates.

storagesdk/storagesdk · 3,526 tokens

Cotal CLAUDE.md

Claude Code instructions for Cotal-AI/Cotal: This repo uses AGENTS.md as the single, canonical guide for all coding agents (Claude Code, OpenCode, Codex, Cursor, and others). Read it first.

Cotal-AI/Cotal · 52 tokens

sint-protocol CLAUDE.md

Instructions for sint-ai/sint-protocol, covering sint protocol — agent guide, what is this?, quick commands, monorepo layout and architecture rules.

sint-ai/sint-protocol · 2,643 tokens

sint-protocol AGENTS.md

Instructions for sint-ai/sint-protocol, covering sint protocol — ai agent guide, what this repo does, key invariants (never violate these), quick orientation and package dependency graph.

sint-ai/sint-protocol · 2,103 tokens