cass
Always search before starting any work across all coding agent session histories (Claude Code, Codex, Cursor, Gemini CLI, Aider, ChatGPT) to find whatever we've discussed before.
What this skill does
# CASS - Coding Agent Session Search Search and explore your AI coding session history across multiple agents. ## Prerequisites Install cass: ```bash # Install via cargo or download binary cargo install cass ``` Build the index: ```bash cass index ``` ## CLI Reference ### Search Sessions ```bash # Basic search cass search "query" --json # With wildcards cass search "react*" --json cass search "*hook*" --json # Limit results cass search "query" --limit 20 --json # Filter by agent cass search "query" --agent claude --json cass search "query" --agent codex --json cass search "query" --agent cursor --json cass search "query" --agent gemini --json cass search "query" --agent aider --json # Filter by workspace/project cass search "query" --workspace /path/to/project --json # Filter by time cass search "query" --days 7 --json # Output detail levels cass search "query" --fields minimal --json # paths only cass search "query" --fields summary --json # default cass search "query" --fields full --json # everything # Highlight matches cass search "query" --highlight --json ``` ### Check Health ```bash # Verify index is healthy before searching cass health ``` ### Build/Rebuild Index ```bash # Full rebuild cass index --full # Watch mode for continuous updates cass index --watch ``` ### View Session Details ```bash # View specific line from search results (path is positional) cass view /path/to/session.jsonl -n 42 --json # With more context lines cass view /path/to/session.jsonl -n 42 -C 10 --json ``` ### Expand Context ```bash # Show surrounding messages around a line (path is positional, -n is required) cass expand /path/to/session.jsonl --line 42 -C 3 --json # More context cass expand /path/to/session.jsonl --line 42 -C 10 --json ``` ### Activity Timeline ```bash # Activity across agents cass timeline --json # Last N days (use relative format) cass timeline --since 7d --json # Today only cass timeline --today --json # By agent cass timeline --agent claude --json # Group by hour or day cass timeline --group-by hour --json cass timeline --group-by day --json ``` ### Export Conversations ```bash # Export to markdown (path is positional) cass export /path/to/session.jsonl --format markdown # Export to HTML cass export /path/to/session.jsonl --format html -o conversation.html # Export to JSON cass export /path/to/session.jsonl --format json # Include tool calls cass export /path/to/session.jsonl --include-tools ``` ### Statistics ```bash # Index statistics cass stats --json ``` ### Capabilities ```bash # Show supported features and connectors cass capabilities --json ``` ### Find Related Sessions ```bash # Find sessions related by workspace, day, or agent (path is positional) cass context /path/to/session.jsonl --json # Limit per relation type cass context /path/to/session.jsonl --limit 3 --json ``` ## Supported Agents - `claude` - Claude Code sessions - `codex` - OpenAI Codex CLI - `cursor` - Cursor IDE - `gemini` - Gemini CLI - `aider` - Aider - `chatgpt` - ChatGPT (if exported) ## Workflow Patterns ### Find Past Solutions ```bash # Search for how you solved something before cass search "authentication jwt" --json cass search "postgres connection pool" --json cass search "react state management" --json ``` ### Review Recent Work ```bash # What did I work on today? cass timeline --today --json # Last week's activity cass timeline --since 7d --json ``` ### Deep Dive into a Session ```bash # 1. Search for topic cass search "bug fix login" --json # 2. Get line number from results, view details cass view /path/from/results.jsonl -n 123 --json # 3. Expand context around interesting parts cass expand /path/from/results.jsonl --line 123 -C 5 --json # 4. Export full conversation for reference cass export /path/from/results.jsonl --format markdown -o reference.md ``` ### Cross-Agent Learning ```bash # How did different agents handle similar problems? cass search "api design" --agent claude --json cass search "api design" --agent codex --json cass search "api design" --agent cursor --json ``` ## Best Practices 1. **Build index first** - Run `cass index` before searching 2. **Check health** - Run `cass health` if searches return no results 3. **Use wildcards** - `*pattern*` for flexible matching 4. **Filter by agent** - When you remember which tool you used 5. **Use timeline** - For temporal exploration 6. **Export valuable sessions** - Save important conversations as markdown
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.