Wrap Insights — Development skill for Claude Code
/wrap with /insights cross-session report (Phase 1b opt-in — measurement mode).
How to install Wrap Insights
Installs to ~/.claude/skills/jstottlemyer-monsterflow-wrap-insights/SKILL.md
mkdir -p ~/.claude/skills/jstottlemyer-monsterflow-wrap-insights && curl -fsSL https://raw.githubusercontent.com/Jstottlemyer/MonsterFlow/HEAD/commands/wrap-insights.md -o ~/.claude/skills/jstottlemyer-monsterflow-wrap-insights/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Wrap Insights does
description: /wrap with /insights cross-session report (Phase 1b opt-in — measurement mode) allowed-tools: Bash, Read, Edit, Glob, Grep, Write
This is `/wrap` with the `insights` argument. Read `commands/wrap.md` in this repo and execute it now as if `$ARGUMENTS` contained `insights` — the rest of the workflow is defined there.
Phase 1b runs the `/insights` cross-session report alongside the normal wrap-up. Note: built-in slash commands like `/insights` must be typed by the user (the m
Alternatives in Development
- Om Weekly — Weekly synthesis — cross-session review of vault activity, North Star alignment, patterns, uncaptured wins, an 4.6k ★
- Ars Citation Check — ARS academic-paper citation-check mode — citation error report 4.5k ★
- Harness Improvement — Update Kandev harness files from session learnings or explicit cross-platform harness requests 697 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Grimoire Dream
Dream Mode — consolidation hors-session, patterns cross-domaine, insights émergents
Wrap Full
/wrap thorough mode — insights + force-run conditional phases (use when stepping away for a stretch)
Agent Insight
Local-first, cross-agent session insights for Claude Code, Codex, Cursor, OpenCode, and Pi.
Collaborate
Opt-in multiplayer mode -- brain-dump together, claim tasks across machines, flag decisions async
Arm Tools
Arm the current project for Solid Forge — provision arch-configs, optional gate dev-deps, constitution, templa
Usage Insights
Cross-client (Claude Code + Codex CLI) usage insights with hybrid evidence + agentic analysis.
Related Agents
Evolve Build Planner
Build-planning agent for the Evolve Loop. Externalizes Builder's internal chain-of-thought design step into an
Session Ender
Session 收尾 agent。當使用者說「收工」「收尾」「session 結束」「wrap up」「session-ender」時使用。依序執行:(1) 從對話中識別 improve signals 並輸出 (2)
Eval Judge
Use this agent during the /eval Skill Phase 3 (Epic #803, issue #810) to judge — from a session-eval record's