skills, subagents and the claude plugin for polygraph
This repository also configures its own agents. See what polygraph-skills tells them →
Hook Claude Code
One of 5 in hooks.json
Runs after a tool call finishes for mcp__plugin_polygraph_.* and mcp__polygraph.* tool calls, executing record-session-mapping.mjs via node. From nrwl/polygraph-skills.
Hook Claude Code
One of 5 in hooks.json
Runs when a session starts on startup, resume and compact, executing reinject-polygraph-context.mjs and record-session-mapping.mjs via node (2 commands). From nrwl/polygraph-skills.
Hook Claude Code
One of 5 in hooks.json
Runs when you submit a prompt, before the agent sees it, executing ensure-agent-session-capture.mjs via node with --detach. From nrwl/polygraph-skills.
Hook Claude Code
One of 5 in hooks.json
Runs when the agent finishes a response, executing ensure-agent-session-capture.mjs via node with --detach. From nrwl/polygraph-skills.
Hook Claude Code
One of 5 in hooks.json
Runs when a session ends, executing finalize-agent-session.mjs via node. From nrwl/polygraph-skills.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: