Claude Code mod
safe-keys
A Claude Code mod. Paste an API key into the chat and it becomes a name everywhere: the transcript on disk, the screen, the model. Your tools still use it as $NAME.
Install
/plugin marketplace add markfulton/safe-keys
/plugin install safe-keys@safe-keysMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: runs processes, writes files, sets env vars, reads files, reads env vars, draws
- Sees
- classic hooks, every prompt, every tool call
- Draws in
any component- Hooks
classic.SessionStartsession.startprompt.editprompt.submitsession.appendtool.callui.renderturn.completesession.endcommand.run
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
- markfulton/safe-keys
- Folder
.- Marketplace
safe-keys- Author
- Mark Fulton
- Website
- club.reinventing.ai/safe-keys
- License
- MIT
- Last updated
- 29 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is safe-keys?
A Claude Code mod. Paste an API key into the chat and it becomes a name everywhere: the transcript on disk, the screen, the model. Your tools still use it as $NAME. It is a mod for Claude Code, from markfulton/safe-keys on GitHub.
What can the safe-keys mod access?
Its widest reach is "writes or runs" (runs processes, writes files, sets env vars, reads files, reads env vars, draws). It sees classic hooks, every prompt, every tool call. It draws in any component. Like any mod, it runs with your permissions.
How do I install safe-keys?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add markfulton/safe-keys and then /plugin install safe-keys@safe-keys.
Is safe-keys popular?
markfulton/safe-keys has 3 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 29 October 2026.
More guard & safety mods
redact-restore
3isandrel/redact-restore
Reversible redaction for Claude Code: private values are replaced with placeholders before the model API sees them and restored locally. No API gateway.
vault
3yocloud-code/claude-vault
Credential vault for Claude Code: macOS Keychain secrets, per-directory grants, injected env, redacted output, pane with import/export
receipt
3yash-gadodia/claude-mods
Keeps a per-turn tally of edits, runs, curls and destructive commands and shows it on the turn footer; a claim with no run flags the spinner, a destructive Bash unfolds its tool group, and an edit-without-run turn suggests running the tests.
waiting-bell
3ibrahimkobeissy/claude-mods
Rings a bell and shows a banner whenever Claude is blocked waiting for you, repeating every 5 minutes until you answer
peek
3alex2481kobe/claude-mods
Images in the terminal: Claude shows the pictures it makes or finds inline, as real pixels in kitty and Ghostty and as a colored-block preview elsewhere
ai-dev-team-office
2111vandit111/ai-dev-team
Optional add-on for ai-dev-team: live agent office band and pane in Claude Code, plus a guard that blocks git writes during an agent-team run
Browse the most popular Claude Code mods, all guard & safety mods, or the skills and MCP server directories.