All Claude Code modsboxiaolanya2008/claudecode-plus-mod
prompt-shield
Strip invisible fingerprint characters from outgoing prompts and audit what the model actually receives.
The scan could not record a complete footprint for prompt-shield, so its access is unknown; it fails claude plugin validate on Claude Code 2.1.302: modules../register.ts: prompt-shield: mods/prompt-shield/hooks/register.ts, compiled line 3 `const ui = $.ui;`: $.ui is used as a value (a noun of $ bound, pas….
- Access: unknown, the footprint is incomplete
- Static scan, not a runtime test
Install hint
/plugin install prompt-shield --marketplace boxiaolanya2008/claudecode-plus-modFrom the repository's own marketplace. Confirm the plugin name in the repository's README before installing. Mods need Claude Code 2.1.287 or later. It fails validation in the latest scan, so it may not install.
Access
Unknown accessThe footprint is unavailable or incomplete.Validation
fails on 2.1.302View the source on GitHub Back to the list
What the scan recorded
- Footprint
- Unavailable or incomplete. Recorded events and calls below may omit access.
- Observed events
- unknown
- Hooks
not reported- API calls
not reported- Validation on 2.1.302
- fails on 2.1.302
- Validator output
- modules../register.ts: prompt-shield: mods/prompt-shield/hooks/register.ts, compiled line 3 `const ui = $.ui;`: $.ui is used as a value (a noun of $ bound, passed or read); $ is always spelled $.noun.event(...) at the call site, on is always on("<event>", hook), and next.to always next.to(e, "<tier>")
- Scanned revision
da207cc489c9- Marketplace passed
- claudecode-plus-mod
These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. How the scan works.
More from boxiaolanya2008/claudecode-plus-mod
- agent-charterPin an agent charter into the system prompt: skills-first workflow, per-language comment standards, commit fo…
- cache-guardStabilize the prompt-cache prefix, audit compaction fidelity, and report real cache hit numbers per turn.
- clear-intentAttach an intent protocol to every prompt: restate the goal, separate confirmed from assumed, ask before acti…
- human-tonePin a house style into the system prompt: direct, human answers with no filler praise or over-formatting.
- plusAll claudecode-plus-mod Mods in one install: prompt-shield, cache-guard, human-tone, clear-intent and agent-c…
Badge for your README
Authors can show the latest scan result in their README. Each badge links to this page.
[](https://mods.aidojo.si/mods/boxiaolanya2008--claudecode-plus-mod--prompt-shield/)
[](https://mods.aidojo.si/mods/boxiaolanya2008--claudecode-plus-mod--prompt-shield/)