dev
278ecca018
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.
12 lines
286 B
Plaintext
12 lines
286 B
Plaintext
# ctxguard runtime state lives in ~/.claude/ctx-guard/ and must NEVER be committed.
|
|
# These entries are a second line of defence in case anything is copied in by hand.
|
|
**/entities.json
|
|
**/policy.json
|
|
**/index.json
|
|
**/audit.jsonl
|
|
**/.ctxguard-cache/
|
|
*.local.md
|
|
__pycache__/
|
|
*.pyc
|
|
.venv/
|