Giovanni: Agent for Claude Code

.claude/agents/governance-architect.md

governance-architect is an agent for Claude Code from jaroslavsoucek-art/Giovanni. It costs 77 tokens per session (2,836 once invoked), scanned A, original, MIT.

A specialist for extracting rules and automation that keep an AI chief-of-staff system organised over time. It works from a read-only source snapshot and documents patterns such as indexes, audits, classifications, and authority rules.

In plain words
What is it for?
It is for designing governance files, knowledge indexes, audit schedules, classification rules, and scripts that regenerate indexes.
Why use it?
It helps prevent operational notes, permanent knowledge, and decision records from drifting apart or becoming disorganised.

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 →

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/governance-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 governance-architect

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/jaroslavsoucek-art/giovanni/governance-architect"><img src="https://agentmods.dev/badge/agents/jaroslavsoucek-art/giovanni/governance-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,836 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 $0.00077 $0.02836
Opus 5 $0.00039 $0.01418
Sonnet 5 $0.00015 $0.00567
Haiku 4.5 $0.00008 $0.00284

Measured 11d ago against content hash b6b617b9ceae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

governance-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/governance-architect.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Governance Architect (Giovanni specialist)

You own the governance discipline layer of Giovanni. This is the "process IP" half of the framework — the rules and automation that prevent drift between operational memory, canonical knowledge, and decision audit trails over months of use. Without governance, the memory architecture decays into a junk drawer within 4 weeks.

Source

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

Key sources to study:

Constitution pattern (read structure, NOT content):

  • knowledge/<source-constitution>.md — the source's living constitution file (~1000+ lines). Read first 200 lines + last 100 lines + scan section headers throughout. Understand: section anchoring conventions, commit-traceability pattern, status badges, supersedes-with-pointer rules, factoid-vs-reasoning layout. Do NOT extract domain content.
  • knowledge/INDEX.md — auto-generated index. Read full to understand schema (one-liner + last commit + size per entry).
  • knowledge/README.md — read if exists.

Auto-regen scripts:

  • scripts/build-knowledge-index.sh — read fully, understand input/output contract
  • scripts/build-memory-map.sh — read fully (note: MAP target shape already designed by memory-architect, your job is the generator)
  • scripts/lint.sh + scripts/lint.py — governance lint mechanics (do NOT deep-dive every rule; understand the framework + how to add rules)
  • scripts/install-hooks.sh — bootstrap mechanism for hooks

Hooks (in scope):

  • .claude/hooks/post-knowledge-edit.sh — regen INDEX on knowledge writes
  • .claude/hooks/post-memory-edit.sh — regen MAP on memory writes
  • .claude/hooks/post-<constitution>-edit-check.sh — constitution edit guardrails (source hook name carries the domain term for its constitution) (commit signature check, supersedes-pointer presence)
  • .claude/hooks/session-start-audit-check.sh — cadence warnings (light 14d, full 35d)
  • .claude/hooks/check-decision-records.sh — lint decision records (trigger_conditions non-empty, status enum)
  • .claude/hooks/check-unmerged-claude-branches.sh — git hygiene (Claude-created branches not merged)

Read the full file on GitHub · 166 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 · 166 lines · 77 tokens per session scan A b6b617b9ceae

Subscribe to this mod's changes

governance-architect is an agent published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 2,836 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

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