Agent Claude Code
IC3/PDR generalization step — given one counterexample-to-induction (CTI), propose ONE new invariant conjunct that blocks it and is as weak as possible. Dispatched by /lean4-ic3. Stateless, single-shot, no file edits.
Command Claude Code
IC3/PDR-style inductive invariant inference — find CTIs, dispatch generalizer, grow a structure-based invariant until inductive.
Command Claude Code
Run diagnostic checks on SageOx configuration and integrations.
Command Claude Code
Command "ox-init" from rupakm/leslie, covering common issues, already initialized, permission denied and not a git repository.
Command Claude Code
Load SageOx team context for this AI coworker session.
Command Claude Code
belongs in the ox CLI JSON output (guidance field), not here. Skills are agent-specific wrappers; ox serves all agents (Codex, etc.). --> Abort a session, discarding all local data without uploading to the ledger. This is destructive and cannot be undone. Use /ox-session-stop to save instead.
Command Claude Code
belongs in the ox CLI JSON output (guidance field), not here. Skills are agent-specific wrappers; ox serves all agents (Codex, etc.). --> List recent sessions from the project ledger and offer to view one.
Command Claude Code
Command "ox-session-review" from rupakm/leslie, covering phase 1 — scan & score (read-only), quality signals, removal candidates, missing/poor summary and poor title.
Command Claude Code
belongs in the ox CLI JSON output (guidance field), not here. Skills are agent-specific wrappers; ox serves all agents (Codex, etc.). Exception: Post-Command sections that require agent-side actions (e.g., displaying a notice, generating a summary) are legitimate here. --> Start recording this agent session to the…
Command Claude Code
belongs in the ox CLI JSON output (guidance field), not here. Skills are agent-specific wrappers; ox serves all agents (Codex, etc.). --> Check the status of all active session recordings in this project.
Command Claude Code
belongs in the ox CLI JSON output (guidance field), not here. Skills are agent-specific wrappers; ox serves all agents (Codex, etc.). Exception: Post-Command sections that require agent-side actions (e.g., displaying a notice, generating a summary) are legitimate here. --> Stop recording and save this agent session to…
Command Claude Code
Check SageOx project status including authentication, sync, and daemon health.
Command Claude Code
Command "ox" from rupakm/leslie, covering sageox commands reference, get project conventions, check project health, update conventions and initialize sageox.
Hook Claude Code
Runs after a tool call finishes, running an inline shell check. From rupakm/leslie.
Hook Claude Code
Runs before the context is compacted, running an inline shell check. From rupakm/leslie.
Hook Claude Code
Runs when a session ends, running an inline shell check. From rupakm/leslie.
Hook Claude Code
Runs when a session starts, running an inline shell check. From rupakm/leslie.
Hook Claude Code
Runs when the agent finishes a response, running an inline shell check. From rupakm/leslie.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, running an inline shell check. From rupakm/leslie.
Settings file Claude Code
Agent settings declaring 6 hook events (PostToolUse, PreCompact, SessionEnd, SessionStart).
Instructions file CodexOpenCode
AGENTS.md instructions for rupakm/leslie, covering ai agent instructions, leslie gadgets, protocol proof guidelines, invariant design: think before proving and proof strategy preferences.
Instructions file
Claude Code instructions for rupakm/leslie.