List past CocoDream distillation sessions from .cocoplus/grove/dream-*.md files, showing timestamp, function count, and lesson candidate count for each session.
Scanned 6/5/2026
Install via CLI
openskills install Snowflake-Labs/cocoplus---
name: "dream-history"
description: "List past CocoDream distillation sessions from .cocoplus/grove/dream-*.md files, showing timestamp, function count, and lesson candidate count for each session."
version: "1.0.1"
author: "CocoPlus"
tags:
- cocoplus
- cododream
---
Your objective is to display a summary of past CocoDream distillation sessions.
## Pre-flight Check
Check that `.cocoplus/` exists. If not:
Output: "CocoPlus not initialized in this directory. Run `$pod init` to begin." Then stop.
## Find Dream Files
Scan `.cocoplus/grove/` for all files matching `dream-*.md`. Sort by timestamp, newest first.
If no dream files found:
Output: "No CocoDream sessions found. Run `$dream` to start your first distillation session." Then stop.
## Read Session Metadata
The `n` argument controls how many sessions to display (default: 3 if not provided).
For each of the most recent n dream files, read:
- Timestamp (from filename: `dream-<timestamp>.md`)
- Function count (from the "Analysed: N functions" line in the file)
- Total lesson candidates (from the "Lesson candidates: N" line)
- Promoted count (count of lessons marked as promoted in the file, if tracking exists; otherwise show as unknown)
## Output
```
CocoDream History (last <n> sessions)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
<timestamp> <N> functions <M> candidates (<K> promoted)
.cocoplus/grove/dream-<timestamp>.md
<timestamp> <N> functions <M> candidates (<K> promoted)
.cocoplus/grove/dream-<timestamp>.md
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
To promote a lesson, run: $patterns promote "<lesson title>"
```
## Anti-Rationalization
| Shortcut / Temptation | Why It Fails |
|-----------------------|--------------|
| Show all sessions without a default limit | Long lists obscure the most recent and relevant sessions; default n=3 is intentional |
## Exit Criteria
- [ ] Sessions displayed newest-first
- [ ] Each session shows timestamp, function count, candidate count, and file path
- [ ] If no sessions exist, actionable message pointing to `$dream` is shown
No comments yet. Be the first to comment!
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. ---
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.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.