Safety & Privacy · Claude Code mod New
budget-guard
Stops a session before it runs past a budget: warns near a cost or plan-window limit, then refuses tool calls and asks before the next prompt.
pii-guard mod
PII de-identification as a mod: placeholders go to the model, real values are restored before Edit, Write and Bash, exfiltrating tools are refused.
Safety & Privacy mod for Claude Code by danyuchn · built on function hooks · runs inside Claude Code
0 votes all time
Install pii-guard mod
Step 0, once: enable function hooks with export CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1 (bash/zsh), $env:CLAUDE_CODE_ENABLE_FUNCTION_HOOKS="1" (PowerShell), or put it under env in ~/.claude/settings.json. Needs Claude Code 2.1.269+. Guide
uv run pii-guard-hookd install --mod
Authordanyuchn ↗
Requiresfunction hooks: CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1, Claude Code 2.1.269+
README badge
[](https://claudemods.ai/mods/pii-guard) About pii-guard mod
The Claude Code front end of pii-guard (Taiwan-focused identifiers, README in Traditional Chinese). Talks to the local pii-guard-hookd service; the mod's tool.call runs before Edit validation, which is the point.
New to mods? Start here. claudemods.ai is an independent catalog, not affiliated with Anthropic. Listings are contributed by the community and link to third-party code. Read the source before installing; mods run inside Claude Code with the permissions of your session. Something wrong with this listing? Tell us.
More in Safety & Privacy
All → Safety & Privacy · Claude Code mod Safety & Privacy · Claude Code mod New
secret-redactor
Swaps secrets, email addresses and IPs for stable placeholders before the model reads them, and restores them on the way into a tool call.
Safety & Privacy · Claude Code mod New
honmoon-redact
Client-side redaction of API keys and sensitive identifiers from Read, Bash and Grep output before it reaches the model.