What is phone-a-team?

A command for giving a task to one or more other AI models, reviewing their replies, and repeating the process for several rounds before producing a combined answer.

Use it for tasks that benefit from delegated work, review, repeated improvement, and a final combined result.

It reduces the need to manually compare suggestions and refine them across multiple AI models.

phone-a-team — Command for Claude Code and Codex by freibergergarcia

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.

Clone the repo

git clone --depth 1 https://github.com/freibergergarcia/phone-a-friend

Made for: Claude Code, Codex.

Or install phone-a-friend, the plugin that ships this one along with the rest of its 4 skills, 3 commands, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/freibergergarcia/phone-a-friend/phone-a-team/github.svg)](https://agentmods.dev/commands/freibergergarcia/phone-a-friend/phone-a-team)

Your own site

<a href="https://agentmods.dev/commands/freibergergarcia/phone-a-friend/phone-a-team"><img src="https://agentmods.dev/badge/commands/freibergergarcia/phone-a-friend/phone-a-team/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/freibergergarcia/phone-a-friend/phone-a-team"><img src="https://agentmods.dev/badge/commands/freibergergarcia/phone-a-friend/phone-a-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 14,878 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 3 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00033	$0.14878
Opus 5	$0.00016	$0.07439
Sonnet 5	$0.00007	$0.02976
Haiku 4.5	$0.00003	$0.01488

Measured 2d ago against content hash 6455bbc86dc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade D, and why

phone-a-team scanned grade D with 3 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

| **Ollama** | `PROMPT_JSON="$(jq -Rs . < "$PROMPT_FILE")"; curl -s http://localhost:11434/api/chat -H "Content-Type: application/json" -d "{\"model\":\"<model>\",\"messages\":[{\"role\":\"user\",\"content\":${PROMPT_JSO

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

`curl -fsSL https://opencode.ai/install | bash`"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| **Ollama** | `PROMPT_JSON="$(jq -Rs . < "$PROMPT_FILE")"; curl -s http://localhost:11434/api/chat -H "Content-Type: application/json" -d "{\"model\":\"<model>\",\"messages\":[{\"role\":\"user\",\"content\":${PROMPT_JSO

commands/phone-a-team.md · 1,209 lines

How it starts

The opening of the file, as written. The whole thing — 1,209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/phone-a-team

Autonomous iterative refinement loop. Delegate a task to one or more backends, review the output, iterate with feedback, and synthesize the final result.

Goal

Take a task description, relay it to backend(s) via phone-a-friend, review the output, iterate up to MAX_ROUNDS rounds until convergence, then present a synthesized result to the user.

Inputs

Task description and options: $ARGUMENTS

Step 0 — Relay mode

command -v phone-a-friend

If found: set RELAY_MODE = binary
If not found: set RELAY_MODE = direct

No hard abort. The skill continues either way.

Direct call reference

When RELAY_MODE = direct, call backend CLIs directly instead of using the phone-a-friend binary:

Backend	Direct command
Codex	`codex exec -C "$PWD" --skip-git-repo-check --sandbox <mode> "$(cat "$PROMPT_FILE")" < /dev/null`
Gemini	`gemini --sandbox --yolo --include-directories "$PWD" --output-format text -m <model> --prompt "$(cat "$PROMPT_FILE")"`
Ollama	`PROMPT_JSON="$(jq -Rs . < "$PROMPT_FILE")"; curl -s http://localhost:11434/api/chat -H "Content-Type: application/json" -d "{\"model\":\"<model>\",\"messages\":[{\"role\":\"user\",\"content\":${PROMPT_JSON}}],\"stream\":false}" \| jq -r '.message.content'`
OpenCode	`opencode run --dir "$PWD" --model <provider/model> "$(cat "$PROMPT_FILE")"` — omit `--model` when no override is set; never pass a bare model name in direct mode (see OpenCode backend below)

Sandbox mapping for direct mode:

Codex: pass the mode string directly (--sandbox read-only or --sandbox workspace-write)
Gemini: --sandbox flag is boolean. Present = sandboxed (read-only). Use --sandbox for both read-only and workspace-write; omit it only for danger-full-access.
Ollama: no sandbox support. All context must be in the prompt.
OpenCode: no sandbox flag is available. --dir "$PWD" scopes the workspace OpenCode reads but does not prevent writes. The user's OpenCode permission config controls file access.

Read the full file on GitHub · 1,209 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.

2d ago Changed · +35 lines 6455bbc86dc3
12d ago First seen · 1,174 lines · 33 tokens per session scan D 604cf02ae484

Subscribe to this mod's changes

phone-a-team is a command published in the GitHub repository freibergergarcia/phone-a-friend (10 stars, last pushed 3d ago), licensed Apache-2.0. It adds 33 tokens to every session and 14,878 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 3 findings (sends data to an external url, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Claude Code ai-agent anthropic cli codex command-line-tool

atomic-plan

Write a design doc (concepts, business rules, approaches) and a checkpoint-table spec (contract) for non-trivial work; inline spec only for trivial. Gauges triviality; loops spec authoring with subagents. Human-facing artifact, Mermaid diagrams allowed.

damusix/atomic-claude · 54 tokens

phone-a-team