teammate-assemble

teammate-assemble is a command for Claude Code from initialneil/project-with-reflect. It costs 27 tokens per session (377 once invoked), scanned A, original, MIT.

A command that connects a sibling workstream to the current one as a live teammate. On macOS with iTerm2 and Claude Code, it opens another terminal window for that workstream.

In plain words
What is it for?
Use it to assemble a teammate workstream, send it work through the project handoff channel, and have it report back while both workstreams remain connected.
Why use it?
It avoids manually opening and configuring the teammate session, and keeps the connection alive so later check-ins can revive it.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Claude Code.

Part of the project-with-reflect plugin — 2 skills, 14 commands, 2 hooks shipped together

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 commands/initialneil/project-with-reflect/teammate-assemble
Clone the repo
git clone --depth 1 https://github.com/initialneil/project-with-reflect

Made for: Claude Code.

Or install project-with-reflect, the plugin that ships this one along with the rest of its 2 skills, 14 commands, 2 hooks.

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 teammate-assemble

README.md
[![agentmods](https://agentmods.dev/badge/commands/initialneil/project-with-reflect/teammate-assemble.svg)](https://agentmods.dev/commands/initialneil/project-with-reflect/teammate-assemble)
Your own site
<a href="https://agentmods.dev/commands/initialneil/project-with-reflect/teammate-assemble"><img src="https://agentmods.dev/badge/commands/initialneil/project-with-reflect/teammate-assemble.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 377 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00027 $0.00377
Opus 5 $0.00014 $0.00188
Sonnet 5 $0.00005 $0.00075
Haiku 4.5 $0.00003 $0.00038

Measured 6d ago against content hash cd1d3b62fe8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

teammate-assemble 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 6d 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.

commands/teammate-assemble.md · 21 lines

What it actually says

Run the teammate-assemble action of the current project's project-with-reflect skill with arguments: $ARGUMENTS

Resolve the project from the current directory first: match $PWD against registry.json projects' repo / dir (the project whose repo contains $PWD). If none matches, ask which project — don't guess. Resolve the commander lane = this session's active workstream (from the last checkin); if this session isn't checked into a workstream, ask which lane commands.

Then follow <project_dir>/SKILL.md's teammate-assemble workflow: run teammate.sh <project_dir> assemble <workstream> --commander <this-lane> — it opens an iTerm2 window running claude "/<project> checkin <workstream> --as-teammate-of <this-lane>", writes the teammate lock, and adds the lane to this lane's stream.json.teammates so every later checkin revives a dead teammate window until /teammate-dismiss. Commanding then goes through the normal vault channel (handoff <workstream> "…" → the teammate's standby watch picks it up).

Claude Code + iTerm2 (macOS) only — if the script fails (no iTerm2 / not macOS), relay its fallback: the exact claude command to run manually in any window; the handoff/pickup protocol works the same.

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. 6d ago First seen · 21 lines · 27 tokens per session scan A cd1d3b62fe8c

Subscribe to this mod's changes

teammate-assemble is a command published in the GitHub repository initialneil/project-with-reflect (13 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 377 once invoked, about $0.0001 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.