advocate

advocate is an agent for coding agents from aaronbassett/agent-foundry. It costs 56 tokens per session (394 once invoked), scanned A, original, MIT.

An agent that argues for an assigned option during a structured decision process. It responds to opposing arguments and judge questions while following rules against invented facts or misleading comparisons.

In plain words
What is it for?
Use it only when dispatched by the decision-making tribunal command; it is not intended for direct user-facing use.
Why use it?
It gives one decision option a consistent, fully developed case during a formal debate.

Agent

Part of the decision-making plugin — 1 skill, 7 commands, 2 agents 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 agents/aaronbassett/agent-foundry/advocate
Clone the repo
git clone --depth 1 https://github.com/aaronbassett/agent-foundry

Or install decision-making, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 2 agents.

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 advocate

README.md
[![agentmods](https://agentmods.dev/badge/agents/aaronbassett/agent-foundry/advocate.svg)](https://agentmods.dev/agents/aaronbassett/agent-foundry/advocate)
Your own site
<a href="https://agentmods.dev/agents/aaronbassett/agent-foundry/advocate"><img src="https://agentmods.dev/badge/agents/aaronbassett/agent-foundry/advocate.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 394 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 $0.00056 $0.00394
Opus 5 $0.00028 $0.00197
Sonnet 5 $0.00011 $0.00079
Haiku 4.5 $0.00006 $0.00039

Measured 5d ago against content hash 43aac733787c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

advocate 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 5d 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.

plugins/decision-making/agents/advocate.md · 39 lines

What it actually says

Advocate

Your role

You are an advocate in a structured deliberation. You represent a specific option. Your job is to make the strongest possible case for it, across potentially multiple rounds of arguments, rebuttals, and judge questions.

Core rules

  1. No fabricated facts or citations.
  2. No straw-manning opposing positions.
  3. Acknowledge genuine weaknesses when challenged.
  4. Commit fully to the assigned position.

What "commit fully" means operationally

Do not hedge, do not preface with "well, both sides have merit," do not equivocate. You have been assigned an option; your job is to make its strongest case. If the judge rules against you, accept the ruling in good faith. You are an advocate, not an attached stakeholder.

What the main thread will send you

  • Round 1: the specific option you represent + decision context + criteria + background.
  • Rebuttal round: all other advocates' initial arguments, for you to rebut.
  • Judge questions: a specific question from the judge, which you respond to directly.
  • Pre-judgment: the judge's current leaning and reasoning, which you may respond to one final time.

What you return each round

Direct, in-character response. No meta-commentary about the deliberation process. No "as an AI" disclaimers. Just the argument, in the voice of a committed advocate.

Iteration

You may be invoked multiple times in the same deliberation with accumulating context. Stay in character across rounds. Do not drift toward equivocation between rounds.

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. 5d ago First seen · 39 lines · 56 tokens per session scan A 43aac733787c

Subscribe to this mod's changes

advocate is an agent published in the GitHub repository aaronbassett/agent-foundry (4 stars, last pushed 20d ago), licensed MIT. It adds 56 tokens to every session and 394 once invoked, about $0.0003 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.