Giovanni: Agent for Claude Code

.claude/agents/adversarial-architect.md

adversarial-architect is an agent for Claude Code from jaroslavsoucek-art/Giovanni. It costs 75 tokens per session (2,396 once invoked), scanned A, original, MIT.

A specialist agent and workflow for challenging important decisions before they are approved. It uses SHIP, REWRITE, or KILL verdicts to judge whether a proposal should proceed, change, or stop.

In plain words
What is it for?
Reviewing proposals, messages, or other deliverables for strategic soundness, counter-cases, and whether they should be sent or pursued.
Why use it?
It adds deliberate critical review so strategic work is tested against strong counterarguments instead of receiving automatic approval.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

This is jaroslavsoucek-art/Giovanni's own configuration. It tells Claude Code how to work on Giovanni itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Giovanni configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/soucek/dev/Giovanni/.claude/agents/deliverable-reviewer.md.

Reuse

Borrowing it

Nothing to install: this file belongs to jaroslavsoucek-art/Giovanni. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jaroslavsoucek-art/Giovanni/main/.claude/agents/adversarial-architect.md
Clone the repo
git clone --depth 1 https://github.com/jaroslavsoucek-art/Giovanni

Made for: Claude Code.

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-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/jaroslavsoucek-art/giovanni/adversarial-architect/github.svg)](https://agentmods.dev/agents/jaroslavsoucek-art/giovanni/adversarial-architect)
Your own site
<a href="https://agentmods.dev/agents/jaroslavsoucek-art/giovanni/adversarial-architect"><img src="https://agentmods.dev/badge/agents/jaroslavsoucek-art/giovanni/adversarial-architect/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-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/jaroslavsoucek-art/giovanni/adversarial-architect"><img src="https://agentmods.dev/badge/agents/jaroslavsoucek-art/giovanni/adversarial-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,396 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 $0.00075 $0.02396
Opus 5 $0.00037 $0.01198
Sonnet 5 $0.00015 $0.00479
Haiku 4.5 $0.00007 $0.00240

Measured 10d ago against content hash 45560c9b0c1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

adversarial-architect 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 10d 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.

.claude/agents/adversarial-architect.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Architect (Giovanni specialist)

You own the adversarial review layer of Giovanni — the policy + workflow + agent that ensures critical pushback is the default mode, not optional flattery. Per gap analysis, this is one of three strongest IP moats: every other AI tool optimizes for being helpful + agreeable; Giovanni's fork user expects SHIP/REWRITE/KILL verdicts, not validation theater.

Your output is policy + agent + workflow, distinct from the operational deliverable-reviewer (which is content QA — consistency, provenance, voice). Adversarial review is strategic — should we send this at all? Is the underlying position right? What's the strongest counter-case?

Source

Read-only snapshot at ~/dev/giovanni-source-snapshot/. Never write to this path.

Key sources:

Agent + workflow:

  • .claude/agents/<domain>-adversarial.md — agent definition (source files carry a domain prefix)
  • .claude/workflows/adversarial-review.md — workflow steps + trigger conditions + verdict format

Policy:

  • CLAUDE.md — find sections on adversarial review, KRITICKÉ PRAVIDLO, KVALITA VÝSTUPŮ — read fully

Cross-architect inputs:

  • /Users/soucek/dev/Giovanni/.claude/agents/deliverable-reviewer.md — distinguish from your scope (content QA vs strategic adversarial)
  • /Users/soucek/dev/Giovanni/memory/templates/brief.template.md — has "Expected pushback" section, your adversarial review extends that thinking
  • /Users/soucek/dev/Giovanni/memory/templates/branch-out.template.md + shadow templates — adversarial lookback is binding rule from prediction-architect
  • /Users/soucek/dev/Giovanni/scripts/lint.py — for optional hook integration

Output target

Write to ~/dev/Giovanni/:

.claude/agents/ — generic adversarial agent (1 file)

  1. .claude/agents/adversarial-reviewer.md — generic operational agent. Trigger: [REVIEW] in draft, "review this", "redline", "before sending", "tear this apart". Default mode: critical, not advisory. Returns SHIP / REWRITE / KILL verdict + prioritized issues. Read-only, never modifies the artifact.

Read the full file on GitHub · 138 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.

  1. 10d ago First seen · 138 lines · 75 tokens per session scan A 45560c9b0c1e

Subscribe to this mod's changes

adversarial-architect is an agent published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 2,396 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

data-engineer

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.

wshobson/agents · 54 tokens

reviewer

A code-review agent that examines changes for correctness, readability, testing, security, consistency, and traceability.

Insajin/autopus-adk · 42 tokens

solid-open-closed-judge

Evaluates code implementation adherence to SOLID Open/Closed Principle (OCP).

closedloop-ai/claude-plugins · 23 tokens

architect

An architecture agent that studies a system and records decisions about its structure, interfaces, dependencies, and future changes.

Insajin/autopus-adk · 39 tokens

design-builder

Use this agent for building production-ready prototypes and implementations from design specs — assembling components into full pages, wiring up interactions, integrating with APIs, setting up project scaffolding, and bridging the gap between design decisions and working software. Dispatch after the design-lead has…

Owl-Listener/designpowers · 85 tokens

inspiration-scout

Use this agent to find aesthetic references, interaction examples, and visual inspiration that match the project brief and the user's taste profile. Dispatched when the team needs creative direction, visual references, or cross-domain inspiration before design begins.

Owl-Listener/designpowers · 50 tokens