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.
18 lines
577 B
JSON
18 lines
577 B
JSON
{
|
|
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
|
|
"name": "ctx-tools",
|
|
"description": "Claude Code plugins for keeping sensitive data out of the model's context",
|
|
"owner": {
|
|
"name": "A.Shakhmatov",
|
|
"email": "dev@shakhmatov.com"
|
|
},
|
|
"plugins": [
|
|
{
|
|
"name": "ctxguard",
|
|
"source": "./plugins/ctxguard",
|
|
"description": "Sanitizes the agent's context: blocks credentials and replaces company names, people and PII with stable reversible aliases before anything reaches the model",
|
|
"version": "1.0.4"
|
|
}
|
|
]
|
|
}
|