Phase 1: Repository & Infrastructure Setup

- Renamed directories: codex-rs -> llmx-rs, codex-cli -> llmx-cli
- Updated package.json files:
  - Root: llmx-monorepo
  - CLI: @llmx/llmx
  - SDK: @llmx/llmx-sdk
- Updated pnpm workspace configuration
- Renamed binary: codex.js -> llmx.js
- Updated environment variables: CODEX_* -> LLMX_*
- Changed repository URLs to valknar/llmx

🤖 Generated with Claude Code

llmx-rs/core/templates/compact/prompt.md

@@ -0,0 +1,9 @@
+You are performing a CONTEXT CHECKPOINT COMPACTION. Create a handoff summary for another LLM that will resume the task.
+
+Include:
+- Current progress and key decisions made
+- Important context, constraints, or user preferences
+- What remains to be done (clear next steps)
+- Any critical data, examples, or references needed to continue
+
+Be concise, structured, and focused on helping the next LLM seamlessly continue the work.

llmx-rs/core/templates/review/exit_interrupted.xml

@@ -0,0 +1,8 @@
+<user_action>
+  <context>User initiated a review task, but was interrupted. If user asks about this, tell them to re-initiate a review with `/review` and wait for it to complete.</context>
+  <action>review</action>
+  <results>
+  None.
+  </results>
+</user_action>
+

llmx-rs/core/templates/review/exit_success.xml

@@ -0,0 +1,8 @@
+<user_action>
+  <context>User initiated a review task. Here's the full review output from reviewer model. User may select one or more comments to resolve.</context>
+  <action>review</action>
+  <results>
+  {results}
+  </results>
+  </user_action>
+

llmx-rs/core/templates/review/history_message_completed.md

@@ -0,0 +1,8 @@
+<user_action>
+  <context>User initiated a review task. Here's the full review output from reviewer model. User may select one or more comments to resolve.</context>
+  <action>review</action>
+  <results>
+  {findings}
+  </results>
+</user_action>
+

llmx-rs/core/templates/review/history_message_interrupted.md

@@ -0,0 +1,8 @@
+<user_action>
+  <context>User initiated a review task, but was interrupted. If user asks about this, tell them to re-initiate a review with `/review` and wait for it to complete.</context>
+  <action>review</action>
+  <results>
+  None.
+  </results>
+</user_action>
+

llmx-rs/core/templates/sandboxing/assessment_prompt.md

@@ -0,0 +1,24 @@
+You are a security analyst evaluating shell commands that were blocked by a sandbox. Given the provided metadata, summarize the command's likely intent and assess the risk to help the user decide whether to approve command execution. Return strictly valid JSON with the keys:
+- description (concise summary of command intent and potential effects, no more than one sentence, use present tense)
+- risk_level ("low", "medium", or "high")
+Risk level examples:
+- low: read-only inspections, listing files, printing configuration, fetching artifacts from trusted sources
+- medium: modifying project files, installing dependencies
+- high: deleting or overwriting data, exfiltrating secrets, escalating privileges, or disabling security controls
+If information is insufficient, choose the most cautious risk level supported by the evidence.
+Respond with JSON only, without markdown code fences or extra commentary.
+
+---
+
+Command metadata:
+Platform: {{ platform }}
+Sandbox policy: {{ sandbox_policy }}
+{% if let Some(roots) = filesystem_roots %}
+Filesystem roots: {{ roots }}
+{% endif %}
+Working directory: {{ working_directory }}
+Command argv: {{ command_argv }}
+Command (joined): {{ command_joined }}
+{% if let Some(message) = sandbox_failure_message %}
+Sandbox failure message: {{ message }}
+{% endif %}