Giovanni: Instructions file for Claude Code

CLAUDE.md

Giovanni CLAUDE.md is an instructions file for Claude Code from jaroslavsoucek-art/Giovanni. It costs 832 tokens per session, scanned A, original, MIT.

Instructions for turning a real project’s working methods into reusable, generic templates. The source project is read for patterns, while names, business details, and other private information are replaced with placeholders.

In plain words
What is it for?
Use them to create sanitized planning templates, specialist-agent instructions, schemas, and examples from an existing project without copying its private domain details.
Why use it?
They prevent project-specific information from leaking into the resulting framework and encourage the agent to question unsuitable or overcomplicated patterns.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

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.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 Giovanni CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jaroslavsoucek-art/giovanni/claude-md"><img src="https://agentmods.dev/badge/instructions/jaroslavsoucek-art/giovanni/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 832 This file is loaded in full into every session.
When invoked 832 The same file — it is already loaded in full.
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 $0.00832 $0.00832
Opus 5 $0.00416 $0.00416
Sonnet 5 $0.00166 $0.00166
Haiku 4.5 $0.00083 $0.00083

Measured 10d ago against content hash dbc4c7bb7693, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

Giovanni CLAUDE.md 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.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Giovanni — Claude Code Instructions (meta-builder mode)

This repo is a methodology framework, not a working assistant. Claude Code sessions here operate in meta-builder mode: read patterns from a source snapshot, produce sanitized generic artifacts in this repo.

Source

The reference implementation lives in ~/dev/giovanni-source-snapshot/ (read-only). Specialist architect agents read from there. Never write to that path.

Critical rules

  1. No domain content carry-over. No stakeholder names, no project codenames, no business specifics from the source. Any source-domain codename, person name, integration partner, or country reference → translate to schema placeholder (<stakeholder_slug>, <project_name>, <integration_partner>, <market>, etc.).
  2. Schema over content. Output templates, not filled examples. One worked example per artifact is fine to show shape — use a synthetic domain (default: solo fintech founder, see docs/test-domain.md).
  3. Critical mode is default. No flattery. No RLHF. Pushback is default. Source has good ideas and bad ideas — flag both. If a pattern in source is over-engineered or domain-specific masquerading as generic, say so and propose a leaner version.
  4. Generic-first thinking. Every template question: "would this work for a portfolio CEO? a solo founder? a consultant? a head of legal?" If only fits one domain shape, redesign.

Specialist architects

Custom subagents live in .claude/agents/. Each has a narrow scope (memory, governance, digest, prediction, stakeholder, adversarial, subagent-roster, slash-command). They read source, output templates + schema explanation to their domain in this repo.

Specialist agents do NOT modify the source snapshot.

Output structure

Giovanni/
├── memory/
│   ├── README.md (schema explanation)
│   ├── templates/ (operational-memory, topic-shard, stakeholder, decision-record, brief, etc.)
│   └── examples/ (worked example using synthetic domain)
├── knowledge/
│   ├── README.md
│   └── constitution.template.md
├── .claude/
│   ├── agents/ (generic specialist agents)
│   ├── commands/ (generic slash commands)
│   ├── hooks/ (auto-regen, audit warnings, etc.)
│   └── workflows/ (digest, branch-out, audit, etc.)
├── docs/
│   ├── setup-guide.md (how to fork + customize for your domain)
│   ├── customization.md (per-layer customization points)
│   ├── test-domain.md (synthetic 2nd domain for pseudo-fork validation)
│   └── origin.md (where this came from)
├── scripts/ (auto-regen, audit cadence checks)
└── examples/ (filled fork on synthetic domain)

Read the full file on GitHub · 66 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 · 66 lines · 832 tokens per session scan A dbc4c7bb7693

Subscribe to this mod's changes

Giovanni CLAUDE.md is an instructions file published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed 2mo ago), licensed MIT. It adds 832 tokens to every session, about $0.0042 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 instructions, from other repositories

agentforge-py copilot-instructions.md

Copilot instructions for Scaffoldic/agentforge-py: See AGENTS.md for project conventions. AGENTS.md is the canonical source for AI-assistant instructions. This file exists so GitHub Copilot's native .github/copilot-instructions.md discovery keeps working.

Scaffoldic/agentforge-py · 101 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens