@zivis/cli 0.1.0-alpha.45 → 0.1.0-alpha.46

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -127,12 +127,14 @@ might break in", "security plan", "categories of attacks".
127
127
  function claudeBlockContent() {
128
128
  return `## ZIVIS
129
129
 
130
- ZIVIS is connected to this project via the \`zivis\` CLI — one agent-neutral command surface, not IDE-specific tooling.
131
-
132
- - Asked to security test or review this repo run \`zivis test\` (or \`zivis test <scope>\` for a focused pass; \`zivis test --list\` shows available scopes) and follow the guidance it returns.
133
- - Asked to threat model this repo run \`zivis threatmodel\` and follow the guidance it returns.
134
- - Use your own repo understanding, reasoning, and shell/tools/browser access as needed these commands are a starting point, not a substitute for judgment.
135
- - Do not treat their output alone as a confirmed finding; verify before reporting.`;
130
+ ZIVIS is connected to this project via the \`zivis\` CLI — one agent-neutral command surface, not IDE-specific tooling. Each command grounds you with the methodology + your app's live security context; you do the work, then submit the result. The submit step is what records the work — skip it and nothing is saved.
131
+
132
+ - Security-test / review → \`zivis test\` (or \`zivis test <scope>\`; \`zivis test --list\` lists scopes). Do the review it grounds, then submit with the \`zivis run complete …\` command it prints — records findings and risks.
133
+ - Threat model \`zivis threatmodel\`, author/update the model, then submit with \`zivis threatmodel sync --input <file.md>\`.
134
+ - Inventory derive the repo's endpoints, tech stack, and top features, write \`{ endpoints?, technologyStack?, features? }\` to JSON, then \`zivis sync --file <inventory.json>\`.
135
+ - Full review or onboarding run all three in one pass: \`zivis test\` (+submit), then \`zivis sync\`, then \`zivis threatmodel\` (+sync). Together they fill findings, risks, endpoints, tech stack, features, and a living threat model.
136
+ - Use your own repo understanding, reasoning, and shell/tools as needed — these commands ground you; they don't replace judgment.
137
+ - Don't treat their output alone as a confirmed finding; verify before reporting.`;
136
138
  }
137
139
  function ruleFileContent() {
138
140
  return `# ZIVIS Security Guidance
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@zivis/cli",
3
- "version": "0.1.0-alpha.45",
3
+ "version": "0.1.0-alpha.46",
4
4
  "description": "ZIVIS CLI — threat modeling, scans, and MCP server for IDE integration",
5
5
  "license": "Apache-2.0",
6
6
  "homepage": "https://zivis.ai",