Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
Install via CLI
openskills install wilbeibi/catchup---
name: catchup
description: Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
---
# catchup
Pull a clean summary of a previous agent session into context.
You are running inside a live session, so bare `catchup` resolves to the newest session in this directory — usually *this one*. Pick the command by what the user wants:
```bash
catchup <agent> --since-compact # another agent's latest session here
catchup --since-compact # recover THIS session after a compaction
catchup <agent> --list # list recent sessions
catchup <agent> -q "topic" # search sessions
catchup <agent>/3 # read 3rd newest session
catchup <agent> --id <id> # read exact session
```
Agents: `codex`, `claude`, `agy` (Antigravity), `opencode`, `pi-agent`.
## Operation
- Default to `--since-compact` (final compaction segment).
- To pick up another agent's work, always name that agent — bare `catchup` finds your own session, not theirs.
- Unclear which session? Run `catchup <agent> --list` first — don't guess.
- Unclear which flag fits the request (full session, `--last N`, a specific rank/id)? Ask the user instead of guessing.
- `-q "topic"` implies `--list` — returns a listing, not a session read.
- To *continue* the same agent's session with full state, suggest the user run `catchup fork` in their terminal — don't transcript-brief when a native fork fits better. To continue in a *different* agent from the terminal, `catchup fork <agent> --into <other-agent>` starts the other agent seeded with the transcript.
- Output: Markdown, conversation only, tool calls/reasoning already stripped; `-i` for metadata only.
Run `catchup --help` for the full flag list.
No comments yet. Be the first to comment!
Scanned 7/10/2026
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.