Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add jaroslavsoucek-art/Giovanni/plugin install 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/skills/jaroslavsoucek-art/giovanni/init)<a href="https://agentmods.dev/skills/jaroslavsoucek-art/giovanni/init"><img src="https://agentmods.dev/badge/skills/jaroslavsoucek-art/giovanni/init/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/skills/jaroslavsoucek-art/giovanni/init"><img src="https://agentmods.dev/badge/skills/jaroslavsoucek-art/giovanni/init.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 | $0.00061 | $0.01027 |
| Opus 5.5 | $0.00024 | $0.00411 |
| Sonnet 5.5 | $0.00012 | $0.00205 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
init 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/giovanni:init
Turn the repo you are in into a Giovanni instance. The plugin is the mechanism (skills, agents, hooks, lint); this skill creates the state the mechanism operates on, in the project, from ${CLAUDE_PLUGIN_ROOT}/skeleton/ and ${CLAUDE_PLUGIN_ROOT}/templates/. This skill is a thin shell around ${CLAUDE_PLUGIN_ROOT}/scripts/init-fork.sh; the script is the procedure.
Usage
/giovanni:init # scaffold the git repo of the cwd; existing files kept
/giovanni:init --force # re-copy templates over existing runtime files (destructive for filled files — ask first)
Pre-flight (binding — STOP on failure)
- Git repo.
git rev-parse --show-toplevelsucceeds. Otherwise STOP: Giovanni's memory is git-tracked by design;git initfirst. - Not the framework repo.
git remote get-url origindoes not matchjaroslavsoucek-art/Giovanni. If it does, STOP and say so — the framework repo is the template, not an instance (the script refuses too;--forceoverrides, which is not something to do on the principal's behalf). --forceis explicit. Only pass it when the principal typed it. It overwritesknowledge/constitution.md,memory/CLAUDE_MEMORY.mdand the other runtime files with blank templates.
Execution flow
- Run, from the repo root:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/init-fork.sh" --yes --project-root "$(git rev-parse --show-toplevel)" $ARGUMENTS - Relay the script's output verbatim: the
+/=lines say what was created and what was kept, the lint block is the fill-in to-do list (placeholders are expected on a fresh scaffold — do not call them errors), the closing block is the next steps. - If the script reported
CLAUDE.md is yours — kept, tell the principal the one line to add to theirCLAUDE.md(@docs/CLAUDE.giovanni.md) and offer to add it. Do not add it unasked. - If the script printed the fork-clone block (
claude plugin marketplace add …), repeat those two commands — they run outside the session. - No commit. Show
git status --shortand stop. The principal reviews the scaffold and commits.
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 · 60 lines · 61 tokens per session scan A bc5ba3043273
init is a skill published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 1,027 once invoked, about $0.0002 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 2026-10-17.
Other skills, from other repositories
Loop
Run the same task on a recurring cron schedule. Parses interval syntax (5m, 2h, 1d, "/15 "), records the schedule, and acknowledges back to the user.
Batch Run
Apply the same prompt or operation to a list of items in turn, collecting results. Useful for "do X to each of these files / PRs / records" tasks.
Get Unstuck
Pause, surface the current plan + open questions, and suggest the next concrete step so the agent (or operator) can recover from a deadlock or analysis paralysis.
V3 CLI Modernization
CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation.
Hooks Automation
Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.
ketchup
Catch the user up on what changed in this chat since their last message, in a few plain sentences and small visuals. Give each action item just enough context to make the call. Use for /ketchup.