Instructions file
Claude Code instructions for kurrent-io/kcap-cli, covering kurrent capacitor cli, what this project does, invariants, tech stack and building.
Instructions file
Claude Code instructions for kurrent-io/kcap-cli, covering kurrent capacitor cli, what this project does, invariants, tech stack and building.
Plugin Claude Code
Plugin marketplace listing 1 plugin: kcap.
Plugin Claude Code
Records and visualizes Claude Code sessions via kcap CLI hooks.
MCP server Claude CodeCodexCursor +2
MCP server "kcap-review" as configured in kurrent-io/kcap-cli. Launched with kcap mcp review.
MCP server Claude CodeCodexCursor +2
MCP server "kcap-sessions" as configured in kurrent-io/kcap-cli. Launched with kcap mcp sessions.
MCP server Claude CodeCodexCursor +2
MCP server "kcap-flows" as configured in kurrent-io/kcap-cli. Launched with kcap mcp flows.
MCP server Claude CodeCodexCursor +2
MCP server "kcap-memory" as configured in kurrent-io/kcap-cli. Launched with kcap mcp memory.
MCP server Claude CodeCodexCursor +2
MCP server "kcap-workitems" as configured in kurrent-io/kcap-cli. Launched with kcap mcp workitems.
MCP server Claude CodeCodexCursor +2
MCP server "kcap-analytics" as configured in kurrent-io/kcap-cli. Launched with kcap mcp analytics.
Hook
Runs when a session starts, executing persist-session-id.sh with --claude and --no-update-check (2 commands). From kurrent-io/kcap-cli.
Hook
Runs when a session ends, running kcap hook --claude --no-update-check. From kurrent-io/kcap-cli.
Hook
Runs when a subagent starts, running kcap hook --claude --no-update-check. From kurrent-io/kcap-cli.
Hook
Runs when a subagent finishes, running kcap hook --claude --no-update-check. From kurrent-io/kcap-cli.
Hook
Runs when the agent sends a notification, running kcap hook --claude --no-update-check. From kurrent-io/kcap-cli.
Hook
Runs when the agent finishes a response, running kcap hook --claude --no-update-check. From kurrent-io/kcap-cli.
Hook
Runs when the agent asks permission for an action, running kcap hook --claude --no-update-check. From kurrent-io/kcap-cli.
Hook
Runs when you submit a prompt, before the agent sees it, executing set-title-prompt.sh. From kurrent-io/kcap-cli.
Skill Claude CodeCodex
This skill should be used ONLY when the user explicitly asks to run a structured agent flow by name or definition id — e.g. "start a flow", "run the code-review flow", "run the X flow", "use flow definition X", "kick off an agent flow", or wants an iterative loop run by a separate hosted participant agent that…
Skill Claude CodeCodex
This skill should be used when the user asks to "disable recording", "stop recording", "delete this session", "don't record this", "remove my session data", "erase this session", "turn off tracking", "stop tracking", "disable kcap", "remove session", or wants to stop the current session from being recorded. Stops the…
Skill Claude CodeCodex
This skill should be used when the user asks to "show errors", "extract errors", "what went wrong", "find tool errors", "review errors from session", "check session errors", "list failures", "what failed in session X", "error report", "show mistakes", or wants to review tool call errors from a recorded session.…
Skill Claude CodeCodex
Guided tour of Kurrent Capacitor for someone who has it installed but does not yet know what it does for them — "what does capacitor do for me", "what is capacitor", "is this thing doing anything", "what can kcap do", "just installed capacitor, now what", "give me a tour", "Start kcap guided tour" (the prompt kcap…
Skill Claude CodeCodex
This skill should be used when the user asks to "hide this session", "make this private", "hide session", "owner only", "make private", "hide from others", "set private", "don't show this session", or wants to change the current session visibility to owner-only. Sets session visibility so only the owner can see it.
Skill Claude CodeCodex
This skill should be used to read, search, or recall past Kurrent Capacitor sessions. Triggers include: "read a previous session", "get session history", "recap session", "what happened in session X", "load context from a previous session", "continue from session", "what did we do last time", "catch me up on session…
Skill Claude CodeCodex
This skill should be used ONLY when the user explicitly asks to run a structured review flow — e.g. "start a review flow", "submit this for review", "re-review after I address findings", or wants an iterative review loop run by a separate reviewer that continues until sign-off. Do NOT use this skill (and do NOT call…