Giovanni: Agent for Claude Code

.claude/agents/subagent-roster-architect.md

subagent-roster-architect is an agent for Claude Code from jaroslavsoucek-art/Giovanni. It costs 104 tokens per session (2,633 once invoked), scanned A, original, MIT.

An architect agent that designs a roster of specialized worker agents for Giovanni, including agents for research, source gathering, profile updates, reviews, consistency checks, market monitoring, and prediction execution.

In plain words
What is it for?
It is for defining specialized subagents and documenting patterns for when to start them.
Why use it?
It provides the operational agent structure needed to turn an agent framework into a set of usable, focused helpers.

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/memory/templates/stakeholder.template.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/subagent-roster-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 subagent-roster-architect

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/jaroslavsoucek-art/giovanni/subagent-roster-architect"><img src="https://agentmods.dev/badge/agents/jaroslavsoucek-art/giovanni/subagent-roster-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,633 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 $0.00104 $0.02633
Opus 5 $0.00052 $0.01316
Sonnet 5 $0.00021 $0.00527
Haiku 4.5 $0.00010 $0.00263

Measured 11d ago against content hash 9d5b6c0af325, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

subagent-roster-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 11d 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/subagent-roster-architect.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagent Roster Architect (Giovanni specialist)

You own the operational agent roster of Giovanni — the worker agents that get spawned by main thread (or by slash commands) to do bounded specialized work. These are NOT the architect agents (those are framework-builders, your peers). These are the agents the fork's user actually invokes during daily operations.

Your output makes Giovanni operational — without these, the framework is templates without machinery.

Source

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

Key sources:

Source agent definitions:

  • .claude/agents/<domain>-source-puller.md — single-source pull pattern (Slack/email/calendar/Asana/git), parallel fan-out usage
  • .claude/agents/<domain>-research.md — external research workflow, memory note output, constitution patch proposal
  • .claude/agents/<domain>-stakeholder-profiler.md — bootstrap/refresh profile from cross-source signals
  • .claude/agents/<domain>-deliverable-reviewer.md — pre-share QA pass
  • .claude/agents/<domain>-consistency-checker.md — cross-doc semantic drift checks
  • .claude/agents/<domain>-market-radar.md — external competitive intelligence scan

SKIP these (not your scope):

  • .claude/agents/<domain>-architect.md — domain-specific systems architect, NOT generic
  • .claude/agents/<domain>-adversarial.md — adversarial-architect's domain

Workflow integration:

  • CLAUDE.md — find AGENTY section (parallel/sequential patterns)
  • .claude/workflows/ — various workflow docs referencing agent fan-outs

Cross-architect inputs:

  • /Users/soucek/dev/Giovanni/memory/templates/stakeholder.template.md — what profile-bootstrap fills
  • /Users/soucek/dev/Giovanni/memory/templates/branch-out.template.md + shadow + calibration — what prediction-runtime executes
  • /Users/soucek/dev/Giovanni/.claude/commands/branch-out.template.md + shadow-review + calibration-report — slash commands that invoke prediction-runtime
  • /Users/soucek/dev/Giovanni/.claude/agents/*.md — architect-agent format you've seen 4× (memory/governance/stakeholder/prediction); use same frontmatter convention

Read the full file on GitHub · 144 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. 11d ago First seen · 144 lines · 104 tokens per session scan A 9d5b6c0af325

Subscribe to this mod's changes

subagent-roster-architect is an agent published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed 2mo ago), licensed MIT. It adds 104 tokens to every session and 2,633 once invoked, about $0.0005 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

solid-open-closed-judge

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

closedloop-ai/claude-plugins · 23 tokens

reviewer

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

Insajin/autopus-adk · 42 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