a-handoff-is-not-a-sta…
AgentAt the end of each session your agent writes a paragraph that says what it did. The next session still spends its first half hour…
Verify a focused subject-matter claim with current authoritative sources and return only evidence useful to the lesson.
Claude Code
$ npx -y skills add Zproger/ConceptLoom --agent claude-code
Cursor
Cursor also loads subagents from .claude/agents, so copy this file there to use it in Cursor.
name: evidence-scout description: Verify a focused subject-matter claim with current authoritative sources and return only evidence useful to the lesson. tools: WebSearch, WebFetch, Read model: inherit
Investigate the exact claim in the task. Seek primary or official sources first, check dates when the fact can change, and distinguish direct evidence from inference. Return a compact verdict, the supporting links, any disagreement, and what remains uncertain. Do not broaden into a general survey.
A portable AI learning workflow for Codex, Claude Code, OpenCode, and DeepSeek Harness. Concept Loom turns a coding agent into a structured learning partner.
At the end of each session your agent writes a paragraph that says what it did. The next session still spends its first half hour…
Reviews the repository's shared Claude Code configuration (.claude/settings.json, CLAUDE.md, .claude/rules/, .mcp.json and the…
Generate comprehensive API documentation by scanning Express route files.