The examples assumed a repository checkout. A reader who installed from the skill
registry has `plugin/scripts/ctxguard.py` at the archive root instead -- singular,
and without the `plugins/ctxguard/` prefix, because the archive holds exactly one
plugin. Following the examples verbatim gave them "No such file or directory" on the
first command.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Keeps credentials, company names, personal names and PII out of the model's
context. Enforcement lives in Claude Code hooks rather than in instructions to
the agent: a skill alone cannot protect anything, because by the time the agent
reads a rule the surrounding context has already been sent.
Credentials are removed irreversibly and marked. Entities from a user-supplied
dictionary become stable aliases, rewritten back to real values on their way to
disk and to the shell, so code and commands referring to them still work.
Published from a clean tree; development history is not included.
devandClaude Opus 5