An AI chief-of-staff runtime that keeps several layers of project memory in the repository and provides digests, stakeholder tracking, review checks, and governance checks. Governance checks are rules that flag contradictions or other process problems.

Maintaining project memory, summarizing changes, tracking stakeholders, reviewing assumptions, and detecting contradictions in repository state.

It helps keep decisions, context, and organizational checks available across sessions instead of relying only on the current conversation.

giovanni — Plugin for Claude Code by jaroslavsoucek-art

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/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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/jaroslavsoucek-art/giovanni/plugin/github.svg)](https://agentmods.dev/plugins/jaroslavsoucek-art/giovanni/plugin)

Your own site

<a href="https://agentmods.dev/plugins/jaroslavsoucek-art/giovanni/plugin"><img src="https://agentmods.dev/badge/plugins/jaroslavsoucek-art/giovanni/plugin/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/jaroslavsoucek-art/giovanni/plugin"><img src="https://agentmods.dev/badge/plugins/jaroslavsoucek-art/giovanni/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 11 skills, 1 command, 9 agents, 4 hooks cost 1,261 tokens a session between them.

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.

Security

Grade A, and why

giovanni 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 today.

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.

plugin/.claude-plugin/plugin.json · 27 lines

What it actually says

{
  "name": "giovanni",
  "displayName": "Giovanni",
  "version": "0.1.1",
  "description": "AI Chief of Staff runtime: 4-layer memory with hard limits, daily digest with drift detection, stakeholder trajectories, invisible shadow hypotheses, adversarial-default review, and a governance lint that fails the build on contradictions. State lives in your repo; the mechanism lives here.",
  "author": {
    "name": "Jaroslav Souček",
    "url": "https://github.com/jaroslavsoucek-art"
  },
  "homepage": "https://github.com/jaroslavsoucek-art/Giovanni",
  "repository": "https://github.com/jaroslavsoucek-art/Giovanni",
  "license": "MIT",
  "icon": "./.claude-plugin/icon.png",
  "documentationUrl": "https://github.com/jaroslavsoucek-art/Giovanni/blob/main/plugin/docs/setup-guide.md",
  "supportUrl": "https://github.com/jaroslavsoucek-art/Giovanni/issues",
  "privacyPolicyUrl": "https://github.com/jaroslavsoucek-art/Giovanni/blob/main/plugin/PRIVACY.md",
  "keywords": [
    "chief-of-staff",
    "memory",
    "digest",
    "governance",
    "stakeholders",
    "prediction",
    "adversarial-review"
  ]
}

Contents

What it installs

The manifest is a name and a version. 11 skills, 1 command, 9 agents, 4 hooks travel with it, and installing the plugin installs all of them — 1,261 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

icon.png 13 KB

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.

today First seen · 27 lines scan A 4c2694cb91d1

Subscribe to this mod's changes

giovanni is a plugin published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-17.

Memory and context Project management agent-framework agentic-ai ai-agents anthropic chief-of-staff

conductor

Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement.

wshobson/agents · not measured

agent-orchestration

Multi-agent system optimization, agent improvement workflows, and context management.

wshobson/agents · not measured

vibe

Vibe sessions, handoff, seed refresh, and ClosedLoop ticket workflows.

closedloop-ai/claude-plugins · not measured

magician

Skills and agents for the software lifecycle in Claude Code: research, design, planning, test-first building, code review, security checks and release. Includes a local code index, per-project workspace notes, stack-specific guidance at session start, and optional Jira and Confluence access.

Alexander-Tyagunov/magician · not measured

ejentum

Ejentum MCP server. Eight tools (four dynamic: reasoning, code, anti-deception, memory; four adaptive: adaptive-reasoning, adaptive-code, adaptive-anti-deception, adaptive-memory) that retrieve task-matched cognitive operations from a library of 679. Each operation is a structured procedure (numbered steps + failure…

ejentum/ejentum-mcp · not measured

g-forge

Educated, enforced project management for AI development - a PM layer, parallel implementation waves, and a git-hook commit gate that can't be skipped. Make any model ship like a senior team.

onlygian/G-Forge · not measured