cross-cli-handshake AGENTS.md

Repository instructions for working on Cross-CLI Handshake, a project that shares agent setup rules across different coding-agent tools.

In plain words
What is it for?
Use them when changing the shared rules, agent profiles, installation process, or participating tool list.
Why use it?
They keep shared guidance, tool-specific details, installation steps, and documentation consistent.

Instructions file for CodexOpenCode

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/jpbaking/cross-cli-handshake/agents-md
Clone the repo
git clone --depth 1 https://github.com/jpbaking/cross-cli-handshake

Made for: Codex, OpenCode.

Per session 146 This file is loaded in full into every session.
When invoked 146 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.00146 $0.00146
Opus 5 $0.00073 $0.00073
Sonnet 5 $0.00029 $0.00029
Haiku 4.5 $0.00015 $0.00015

Measured yesterday against content hash fc25bb965972, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

cross-cli-handshake AGENTS.md scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`~/.gemini/config/rules/`.
AGENTS.md · 16 lines

What it actually says

cross-cli-handshake repository instructions

Follow the Portable Agent Authoring guides for harness discovery and persistent instructions.

  • Keep rules/shared/core.md orchestrator-neutral.
  • Keep host-specific invocation details in the delegate profiles.
  • Install the shared files once under ~/.agents/rules/ and merge one marker-guarded pointer into each participating host's global instruction file.
  • Never maintain a second Antigravity rule copy under ~/.gemini/config/rules/.
  • Update AGENT-INSTALL.md and README whenever the handshake, host paths, or participant set changes.
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. yesterday First seen · 16 lines · 146 tokens per session scan B fc25bb965972

Subscribe to this mod's changes

cross-cli-handshake AGENTS.md is an instructions file published in the GitHub repository jpbaking/cross-cli-handshake (1 stars, last pushed 1mo ago), licensed 0BSD. It adds 146 tokens to every session, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

ai-driven-development AGENTS.md

Instructions for CodeAlive-AI/ai-driven-development, covering ai-driven development — development guide, git publishing defaults, when to create tags and releases, requires a new tag/release and does not require a new tag/release.

CodeAlive-AI/ai-driven-development · 1,110 tokens

kimi-plugin-cross-platform AGENTS.md

AGENTS.md instructions for luhfilho/kimi-plugin-cross-platform, covering agents.md, what this is, commands, run a single test file and do not "simplify" the test runner.

luhfilho/kimi-plugin-cross-platform · 1,577 tokens

IDE-Adapter CLAUDE.md

Instructions for godstale/IDE-Adapter, covering claude.md, commands, architecture, adding a new handler and protocol rules.

godstale/IDE-Adapter · 1,398 tokens

ai-driven-development CLAUDE.md

Instructions for CodeAlive-AI/ai-driven-development, a project described as: Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, Antigravity, and any agent supporting the Agent Skills standard.

CodeAlive-AI/ai-driven-development · 5 tokens

IDE-Adapter GEMINI.md

Instructions for godstale/IDE-Adapter, covering gemini.md, project overview, building and running and development conventions.

godstale/IDE-Adapter · 693 tokens

HelmForge AGENTS.md

AGENTS.md instructions for hhx465453939/HelmForge, covering agents.md - helmforge (codex cli), 主调度, available skills, 主调度分诊路由 and 典型联动链路.

hhx465453939/HelmForge · 1,072 tokens