Delegate independent tasks to specialized agents working concurrently with isolated context.
Session Search
cc-session-search
Search Claude Code conversation history. Use when user asks "where did I discuss X", "when did we talk about X", "find the conversation about X", or wants to continue previous work.
SKILL.md
Full skill instructions
Session Search
Search and analyze Claude Code conversation history.
For storage internals (sessions-index.json, /rename scope, path encoding): See cc-internals skill.
Quick Reference
| Fact | Value |
|---|---|
| Sessions location | ~/.claude/projects/<encoded-path>/ |
| Session format | JSONL (one JSON object per line) |
| Main sessions | <uuid>.jsonl |
| Subagent sessions | agent-<hash>.jsonl |
Tool Selection
| Task | Use This | NOT This |
|---|---|---|
| Pattern search | CC Grep tool | rg via Bash |
| Read files | CC Read tool | cat via Bash |
| Find files | CC Glob tool | find via Bash |
| JSON extraction | jq via Bash | (no CC equivalent) |
Why CC tools: Better permissions, structured output, error handling. Why Bash for jq: No native JSONL parsing in CC.
JSONL Message Structure
{
"type": "user" | "assistant" | "summary",
"timestamp": "<ISO-8601>",
"message": { "content": [{ "type": "text", "text": "..." }] },
"uuid": "<uuid>",
"sessionId": "<uuid>"
}
Search Approach
Step 1: Use CC Grep tool to find matching sessions
Grep pattern="X" path="~/.claude/projects/" output_mode="files_with_matches"
Step 2: Use Bash + jq for JSON extraction
jq -c 'select(.type=="user") | select(.message.content[].text | test("pattern";"i"))' file.jsonl
Step 3: Use CC Read tool to examine specific session content
Query Workflows
"Where did I discuss X?"
- Grep tool → find matching session files
- Decode paths to project names
- Bash + jq → extract first timestamp + context
- Report: project, session ID, date range, snippet
"When did we discuss X?"
- Grep tool → find matching files
- Bash + jq → extract timestamps from matches
- Report: timeline grouped by date/project
"Continue work on X"
- Grep tool → find sessions mentioning X
- Read tool → examine most relevant session
- Analyze: goal, accomplishments, pending items, decisions
- Generate continuation prompt (see template below)
Continuation Prompt Template
Continuing work from [date] on [project]:
## Original Goal
[from first user message]
## What Was Done
- [accomplishments]
- [files changed]
## Pending
- [incomplete items]
## Key Decisions
- [choices that carry forward]
## Resume Point
[specific next task]
jq Patterns
# Decode project path (inline)
echo "-Users-foo-bar" | sed 's/^-/\//; s/-/\//g'
# Extract timestamps from session
jq -r '.timestamp // empty' file.jsonl | sort
# User messages only
jq -c 'select(.type=="user")' file.jsonl
# Filter by text content
jq -c 'select(.message.content[].text | test("pattern";"i"))' file.jsonl
# Get first/last timestamp
jq -rs '[.[].timestamp | select(.)] | sort | .[0], .[-1]' file.jsonl
Related Skills
| Topic | Skill |
|---|---|
| Storage internals, /rename | cc-internals |
| Permission config | cc-configuring-permissions |
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
