Claude Code mod
reference
Référence : un seul panneau en lecture seule, onglets Config (toute la config de Claude Code, secrets masqués), Guide (mode d'emploi des mods), Scénarios (modèle et effort par rôle, « Appliquer ce scénario » note le choix dans ~/.claude/scenarios/applied.json et montre l'écart, sans jamais toucher settings ni agents), Santé (mods chargés, erreurs, CPU), CI (routage et Diagramme avec Gantt et ETA), À essayer (fonctions et idées des recherches, état jamais/en test/adopté/écarté, test, coût, risque, ce qu'on doit tester), R&D (index des recherches, Exporter vers eta), Repos (état, PR, Mettre à jour sur clic) et Exporter pour audit (/audit-export, zip masqué). Les anciennes commandes /config-claude, /control, /mods-guide, /scenarios, /sante, /ci restent quand leur mod n'est pas chargé. /reference
Install
git clone https://github.com/julian-passebecq/claude-mod.git
claude --plugin-dir ./claude-mod/mods/referenceThe repo has no marketplace file, so load the plugin folder directly with --plugin-dir.
What it can access
- Reach
- L2Writes or runs: runs processes, writes files, writes the clipboard, reads files, reads env vars, draws
- Draws in
Pane- Hooks
session.startcommand.runui.render
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- julian-passebecq/claude-mod
- Folder
mods/reference- Author
- Julian Passebecq
- License
- MIT
- Last updated
- 5 November 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is reference?
Référence : un seul panneau en lecture seule, onglets Config (toute la config de Claude Code, secrets masqués), Guide (mode d'emploi des mods), Scénarios (modèle et effort par rôle, « Appliquer ce scénario » note le choix dans ~/.claude/scenarios/applied.json et montre l'écart, sans jamais toucher settings ni agents), Santé (mods chargés, erreurs, CPU), CI (routage et Diagramme avec Gantt et ETA), À essayer (fonctions et idées des recherches, état jamais/en test/adopté/écarté, test, coût, risque, ce qu'on doit tester), R&D (index des recherches, Exporter vers eta), Repos (état, PR, Mettre à jour sur clic) et Exporter pour audit (/audit-export, zip masqué). Les anciennes commandes /config-claude, /control, /mods-guide, /scenarios, /sante, /ci restent quand leur mod n'est pas chargé. /reference It is a mod for Claude Code, from julian-passebecq/claude-mod on GitHub.
What can the reference mod access?
Its widest reach is "writes or runs" (runs processes, writes files, writes the clipboard, reads files, reads env vars, draws). It draws in Pane. Like any mod, it runs with your permissions.
How do I install reference?
Clone julian-passebecq/claude-mod and start Claude Code with --plugin-dir pointing at the mod's folder (mods/reference).
More guard & safety mods
redact
aecheman27-gif/claude-mods
Redacts secrets and PII from every row Claude Code stores and from the CLAUDE.md and memory context, before the model reads it and before the transcript keeps it. Restores a value only into a file that already holds it. No network, no processes, no file writes.
shot-peek
chami1221-eng/my-ai-workbench
When Claude reads an image from the Screenshots folder, shows its file name and capture time above the prompt so you can confirm it read the screenshot you meant.
publish-guard
pomesaka/dotclaude
Before the agent pushes from a repository that has scripts/check-public.sh, runs that check and blocks the push when it finds names or keys that must not be published
aim-widget
5oMaN-Rod/claude-code-widgets
Where a command lands outside this folder: the kube context, cloud profile, Terraform workspace or database it is aimed at, named in the permission dialog
blast-radius
harshitmywork17/claude-mods
Catches risky shell commands (rm -rf, git reset --hard, force push, ...) before they run, forces a permission prompt, and shows what they would touch in a side pane.
prod-guard
6Plagemes/claude-mods
Stops production-affecting commands (terraform apply, kubectl on prod, DROP TABLE) unless explicitly allowed.
Browse the most popular Claude Code mods, all guard & safety mods, or the skills and MCP server directories.