agentmods.dev

claude-warp-team-agents CLAUDE.md

A Claude Code plugin that opens a separate Warp terminal pane for each teammate in Claude’s experimental Agent Teams feature. Warp is a macOS terminal application.

In plain words
What is it for?
Running multiple Claude Code teammates on macOS with Warp, provided Agent Teams is enabled, jq is installed, and Warp has accessibility permission.
Why use it?
It keeps parallel AI workers in separate visible terminal panes and handles starting them, selecting their model, and retrying pane input when needed.

Instructions file

5 4mo ago A scan 290 tokens original MIT
View the source file codercodingthecode/claude-warp-team-agents
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/codercodingthecode/claude-warp-team-agents/claude-md
Clone the repo
git clone --depth 1 https://github.com/codercodingthecode/claude-warp-team-agents
Per session 290 This file is loaded in full into every session.
When invoked 290 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 $0.00290 $0.00290
Opus 5 $0.00145 $0.00145
Sonnet 5 $0.00058 $0.00058
Haiku 4.5 $0.00029 $0.00029

Measured 2d ago against content hash e92a625c0eaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-warp-team-agents 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 2d 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.

CLAUDE.md · 33 lines

What it actually says

warp-agent-teams plugin

Claude Code plugin that auto-splits Warp terminal panes for Agent Teams teammates on macOS.

Plugin structure

.claude-plugin/plugin.json   — plugin manifest (name, version, hooks path)
hooks/hooks.json             — hook registration (PostToolUse/Agent)
hooks/post-agent.sh          — hook entry point
hooks/lib/warp-teammate.sh   — CLAUDE_CODE_TEAMMATE_COMMAND wrapper
hooks/lib/pane.sh            — Warp pane splitting (AppleScript + verify/retry)
hooks/lib/payload.sh         — JSON payload parsing
hooks/lib/warp.sh            — Warp terminal detection
tests/                       — unit tests

How it works

When a teammate is spawned via Agent Teams, CLAUDE_CODE_TEAMMATE_COMMAND points to warp-teammate.sh, which:

  1. Locates the real claude binary
  2. Resolves the model (agent config → parent session → caller default)
  3. Opens a Warp split pane via AppleScript
  4. Runs the teammate in the new pane with verify+retry for Enter reliability

Requirements

  • macOS only
  • Warp terminal
  • jq installed (brew install jq)
  • CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in Claude Code settings
  • Accessibility permissions for Warp (System Settings → Privacy → Accessibility)
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. 2d ago First seen · 33 lines · 290 tokens per session scan A e92a625c0eaa

Subscribe to this mod's changes

claude-warp-team-agents CLAUDE.md is an instructions file published in the GitHub repository codercodingthecode/claude-warp-team-agents (5 stars, last pushed 4mo ago), licensed MIT. It adds 290 tokens to every session, about $0.0014 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.

Building agents
Related

Other instructions, from other repositories

ii-agent AGENTS.md

Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.

Intelligent-Internet/ii-agent · 3,294 tokens

spellbook AGENTS.md

Instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.

majiayu000/spellbook · 910 tokens

open-supermarkets AGENTS.md

Instructions for abracadabra50/open-supermarkets, covering agent integration guide, supported frameworks, quick integration, 1. add as skill and 2. agent calls commands.

abracadabra50/open-supermarkets · 3,643 tokens

helm copilot-instructions.md

Instructions for PetePeter/helm, covering gamepad-cli-hub — copilot instructions, project purpose, system overview, data flow pipeline and key controls.

PetePeter/helm · 6,272 tokens

flyto-core CLAUDE.md

Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.

flytohub/flyto-core · 367 tokens

fusion-skills AGENTS.md

AGENTS.md instructions for CrowdStrike/fusion-skills, covering agents.md, what this is, prerequisites, repository structure and skills ecosystem.

CrowdStrike/fusion-skills · 2,473 tokens