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.
git clone --depth 1 https://github.com/freibergergarcia/phone-a-friendWrote 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.
[](https://agentmods.dev/plugins/freibergergarcia/phone-a-friend/claude)<a href="https://agentmods.dev/plugins/freibergergarcia/phone-a-friend/claude"><img src="https://agentmods.dev/badge/plugins/freibergergarcia/phone-a-friend/claude/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.
<a href="https://agentmods.dev/plugins/freibergergarcia/phone-a-friend/claude"><img src="https://agentmods.dev/badge/plugins/freibergergarcia/phone-a-friend/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
phone-a-friend 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 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.
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.
What it actually says
{
"name": "phone-a-friend",
"displayName": "Phone a Friend",
"description": "Get second opinions, repository reviews, structured Q&A and multi-backend team feedback in local Claude Code. Relay to separately configured Antigravity, Codex, Gemini, Claude, OpenCode, pi or Ollama backends. Full operation requires Node.js 22.13+, the phone-a-friend CLI on PATH, and backend accounts or model servers. Installation does not install or authenticate them. Requests reach the selected provider; PaF keeps local history by default.",
"version": "4.13.5",
"author": {
"name": "Bruno Freiberger"
},
"homepage": "https://github.com/freibergergarcia/phone-a-friend#readme",
"repository": "https://github.com/freibergergarcia/phone-a-friend",
"license": "Apache-2.0",
"keywords": [
"ai-agent",
"claude-code",
"antigravity",
"codex",
"gemini",
"ollama",
"opencode",
"code-review",
"multi-agent",
"cli",
"pi"
]
}
What it installs
The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 86 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed 335421865622
- 5d ago Changed 415f45d7e72e
- 7d ago First seen · 26 lines scan A e31fa062873a
phone-a-friend is a plugin published in the GitHub repository freibergergarcia/phone-a-friend (10 stars, last pushed 2d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-03.
Other plugins, from other repositories
diffctx
Selects the minimum code an LLM needs to review a git diff.
conductor
Hooks, MCP tools, and skills for Claude Code sessions running inside Conductor TUI.
wisp-agentdiff
Per-agent diff review for Claude Code parallel subagent workflows. Each subagent worktree captured automatically, tabbed TUI to approve, revert, or merge each one independently.
wisp-agentdiff marketplace
Plugin marketplace listing 1 plugin: wisp-agentdiff.
roundtable
Convene a round table of frontier AI models — Grok, Codex/OpenAI, GLM, MiniMax, Claude, and Gemini — for independent perspectives and chaired deliberation to consensus. Drives the globally-installed roundtable CLI (install: curl -fsSL https://roundtable.sh/install.sh | bash).
pr-provenance-stamp
Embeds a reviewer-facing provenance receipt into your PR body when Claude runs gh pr create (or glab mr create). A PostToolUse hook (async, zero added latency) records a per-session ledger: tool calls, agent-authored lines, and every test/typecheck command with its real exit code; a PreToolUse (Bash) hook then rewr.