adversarial-author

adversarial-author is an agent for OpenCode from intent-driven-dev/intent-driven-template. It costs 8 tokens per session (219 once invoked), scanned A, original, MIT.

An authoring role for producing a first draft of a requested artifact in a review-based workflow. It follows the supplied requirements and template, records assumptions, and does not edit files or run tools.

In plain words
What is it for?
Use it to draft plans, specifications, or other structured artifacts with required headings and author notes.
Why use it?
It separates initial drafting from later review, making missing requirements and trade-offs easier for another agent to examine.

Agent for OpenCode

Written for OpenCode: installed under .opencode/. Also seen: model in frontmatter; mentions subagents; mentions OpenCode.

Good fit Use it to draft plans, specifications, or other structured artifacts with required headings and author notes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/intent-driven-dev/intent-driven-template/adversarial-author
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/intent-driven-dev/intent-driven-template

Made for: OpenCode.

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 adversarial-author

README.md
[![agentmods](https://agentmods.dev/badge/agents/intent-driven-dev/intent-driven-template/adversarial-author/github.svg)](https://agentmods.dev/agents/intent-driven-dev/intent-driven-template/adversarial-author)
Your own site
<a href="https://agentmods.dev/agents/intent-driven-dev/intent-driven-template/adversarial-author"><img src="https://agentmods.dev/badge/agents/intent-driven-dev/intent-driven-template/adversarial-author/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.

agentmods 80×15 button for adversarial-author

Your own site · 80×15
<a href="https://agentmods.dev/agents/intent-driven-dev/intent-driven-template/adversarial-author"><img src="https://agentmods.dev/badge/agents/intent-driven-dev/intent-driven-template/adversarial-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 219 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00008 $0.00219
Opus 5 $0.00004 $0.00110
Sonnet 5 $0.00002 $0.00044
Haiku 4.5 $0.00001 $0.00022

Measured yesterday against content hash 1306cf7e68d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

adversarial-author 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.

.opencode/agent/adversarial-author.md · 35 lines

What it actually says

You are the author in an adversarial authoring workflow.

Your job is to produce a strong initial draft for the requested artifact or task. You are not the final writer; the primary agent will synthesize your draft with a separate review.

Responsibilities

  • Follow the user's request, artifact template, project context, and artifact-specific rules.
  • Preserve required headings and structure exactly when a template is provided.
  • Make concrete product and implementation decisions when the context supports them.
  • Call out assumptions explicitly when they affect scope or behavior.
  • Keep the draft clean, direct, and ready for review.

Output Format

Return only:

## Draft
<The complete draft artifact or task output.>

## Author Notes
- <Important assumption, decision, or tradeoff>

Do not edit files. Do not run tools. Do not include hidden reasoning or raw chain-of-thought.

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. yesterday First seen · 35 lines · 8 tokens per session scan A 1306cf7e68d1

Subscribe to this mod's changes

adversarial-author is an agent published in the GitHub repository intent-driven-dev/intent-driven-template (126 stars, last pushed 2d ago), licensed MIT. It adds 8 tokens to every session and 219 once invoked, about $0.0000 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 2026-09-07.