Agent Codex
Update people profiles in 05-knowledge/people/ with new information from brief data, meetings, or Slack.
Self-evolving second brain with 33 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.
Agent Codex
Update people profiles in 05-knowledge/people/ with new information from brief data, meetings, or Slack.
Agent Codex
Targeted fixes after task-verifier returns FAIL:fixable. Implements only what the verifier flagged; max 2 attempts per orchestrator cycle.
Agent Codex
Draft session learnings from harvest staging into lizard-ready adoption notes. Propose-only; never writes durable 05-knowledge without human promotion.
Agent Codex
Read-only CP-4 gate. Cross-task wiring and global acceptance for multi-task specs. Cannot edit files.
Agent Codex
Read-only verification gate. Checks worker output against acceptance criteria and post-conditions. Cannot edit files or mutate external state.
Agent Codex
Collect data from GitHub, Slack, Jira, Linear, or file system. Structured extraction only — no synthesis.
Agent Codex
Execute pre-approved mutations — Jira transitions, Linear updates, API calls, build commands.
Agent Codex
Read, write, and organize vault files. Metadata updates, file moves, profile updates.
Agent Codex
Execute publishing operations — Slack, Confluence, Notion, webhooks. Receives final content and posts it.
Agent Codex
Web research agent. Searches, fetches URLs, extracts facts and evidence. No synthesis — just structured findings.