Search and recall previous Claude Code conversation sessions. Use this skill whenever the user asks to remember, recall, find, or look up something from a past conversation or session. Triggers on phrases like: 'remember when we...', 'what did we do about...', 'find that conversation where...', 'when did I last work on...', 'what was that command/approach/solution we used for...', 'look up my past sessions about...'. Also use this skill when the user references prior work context that isn't in the current session, asks to continue work from a previous session, or wants to find a specific discussion, decision, or code snippet from their conversation history. Even vague references to past work ('that thing we did', 'the approach from last week') should trigger this skill.
From bopen-toolsnpx claudepluginhub b-open-io/claude-plugins --plugin bopen-toolsThis skill uses the workspace's default tool permissions.
scripts/search.pySearches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Recall and search previous Claude Code conversation sessions to find past discussions, decisions, solutions, and context.
This skill searches conversation history using two backends:
~/.scribe/scribe.db with 141K+ indexed messages across all AI coding tool sessions. BM25-ranked results, grouped by session.~/.claude/projects/ JSONL conversation files when Scribe isn't available.The search script at scripts/search.py handles both backends automatically.
Run the search script with the user's query:
python3 "SKILL_DIR/scripts/search.py" "<query>" [options]
Options:
| Flag | Purpose |
|---|---|
--project <path> | Filter by project path (substring) |
--recent <days> | Only search last N days |
--limit <n> | Max results (default: 10) |
--full | Force JSONL search (skip Scribe DB) |
--json | Machine-readable output |
--session <id> | Read a specific session's messages |
--recency-weight <f> | Recency weight factor (default: 0.2) |
--half-life <days> | Recency half-life in days (default: 30) |
--no-recency | Disable recency weighting |
Results are ranked by a blend of BM25 relevance and recency. Recent conversations get a boost that decays exponentially (30-day half-life). Use --no-recency to disable.
Crafting good queries:
"stripe webhook", "bap identity", "deploy railway"--project or --recent filters--full for deeper searchSummarize what you found in a clear format:
If the user wants more detail from a specific session:
python3 "SKILL_DIR/scripts/search.py" --session <session-id> --json
This returns the full conversation transcript. Summarize the relevant portions — don't dump the whole thing.
If neither search backend returns results, you can read the JSONL files directly:
# List all project directories
ls ~/.claude/projects/
# List sessions in a specific project
ls ~/.claude/projects/-Users-satchmo-code-myapp/*.jsonl
# The JSONL format has one JSON object per line with these types:
# user — message.content is the user's input
# assistant — message.content is Claude's response (array of text/tool_use blocks)
# progress — tool execution progress
# system — system messages
Session index files (where available) provide quick metadata:
# Check for pre-built session index
cat ~/.claude/projects/<project-dir>/sessions-index.json
# Contains: sessionId, firstPrompt, summary, created, modified, gitBranch, messageCount
cd ~/code/scribe && bun run packages/cli/src/index.ts scan chat --provider claude--project to narrow.69ad65a8-7499-4fd1-9bae-a3f0fcbb11ed. When presenting results, include session IDs so the user can ask for deep dives.