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.
curl -O https://raw.githubusercontent.com/jaroslavsoucek-art/Giovanni/main/CLAUDE.mdgit clone --depth 1 https://github.com/jaroslavsoucek-art/GiovanniWrote 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.
[](https://agentmods.dev/instructions/jaroslavsoucek-art/giovanni/claude-md)<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.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01761 | $0.01761 |
| Opus 5.5 | $0.00704 | $0.00704 |
| Sonnet 5.5 | $0.00352 | $0.00352 |
| Haiku 4.5 | $0.00176 | $0.00176 |
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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 88 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 the live reference implementation, produce sanitized generic artifacts in this repo.
Source
Giovanni is distilled from a live AI Chief of Staff implementation. Resolve its path with bash scripts/source-path.sh, which reads $GIOVANNI_SOURCE or the gitignored .source-path. Architect agents read from there. Read-only: never write to that path, never commit there.
Why live, and not a snapshot
This used to point at a frozen copy, and the copy is why you are reading this. A snapshot stops the day it is taken; the source does not. Three months later the framework was behind its own source by 58 apparatus commits — most of them the interesting kind, rules written after something broke — and nothing in the repo showed it, because every architect was still reading a copy that looked complete.
A frozen source makes the drift invisible and unmeasurable: no diff, no date, no signal. Reading live means the gap between framework and source is always one git log away.
What reading live costs you
- The source moves under you. Anything extracted records the source commit it came from (
bash scripts/source-path.sh --sha). An unanchored "the source does X" rots like any other unanchored claim, and nobody can re-check it. - It is somebody's working repo. A stray write is damage to live operational state. Read-only is not a convention here, it is the rule.
- It is full of live domain content — current names, numbers, open decisions, profiles of real people. The no-leak rule below is what makes reading live safe, and it is the thing to get right before the extraction, not in review.
- The pointer stays off GitHub. This repo is public; the source is a private operational repo whose name identifies the domain this framework was deliberately sanitised of.
.source-pathand the framework's owndocs/governance.config.yaml(whose denylist is a list of that domain's proper nouns) are gitignored for that reason. Forks commit their own config — see.gitignore.
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.
- 9d ago Changed · -2 lines · +260 tokens per session cf8d0b126710
- 1mo ago Changed · +24 lines · +669 tokens per session eaf0381c8be2
- 1mo ago First seen · 66 lines · 832 tokens per session scan A dbc4c7bb7693
Giovanni CLAUDE.md is an instructions file published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed 2d ago), licensed MIT. It adds 1,761 tokens to every session, about $0.0070 per session on Opus 5.5. 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.
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.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).