Skill

Fail

Audit score 45

history-insight

ai-native-camp/camp-2

Access, capture, and analyze Claude Code session history for insights and reference.

What is history-insight?

This skill extracts and analyzes Claude Code session history from local project files. Use it when you need to save, review, summarize, or reference past conversations and work within a coding session.

Locate and read session history files from ~/.claude/projects/
Parse JSONL session data and extract user messages and interactions
Automatically handle large session files with batch processing and parallel analysis
Filter sessions by date and project scope (current project or all sessions)
Generate summaries and insights from captured session data
Handle preprocessing and compression of large files

How to install history-insight

npx skills add https://github.com/ai-native-camp/camp-2 --skill history-insight

Prerequisites

jq must be installed (brew install jq on macOS)
Access to ~/.claude/projects/ directory where session files are stored

Claude Code

Cursor

Windsurf

Cline

How to use history-insight

1.Invoke the skill when you mention capturing, saving, or referencing session history
2.Specify scope: current project only or all Claude Code sessions (or answer the prompt)
3.The skill locates .jsonl session files in the appropriate directory
4.For 1-3 files, sessions are read directly; for 4+ files, batch processing is used
5.Review the extracted insights and captured session data in the report

Use cases

Good for

Save and review what was discussed in today's coding session
Extract key decisions and code changes from a multi-day project
Summarize conversation history for documentation or handoff
Search across all Claude Code sessions for patterns or past solutions
Capture session context before closing a project

Who it's for

Developers using Claude Code for extended projects
Teams needing session documentation and knowledge capture
Users reviewing past work or extracting learnings from sessions

history-insight FAQ

Where are my session files stored?

Session files are stored in ~/.claude/projects/<encoded-cwd>/*.jsonl, where the directory name is an encoded version of your project path (e.g., /Users/foo/project becomes -Users-foo-project).

What happens if I have many session files?

For 4 or more files, the skill uses a batch extract pipeline with parallel Task processing to efficiently analyze all sessions without hitting token limits.

Can I filter sessions by date?

Yes. The skill checks file modification time (mtime) and can filter sessions by date range using OS-specific stat commands.

What if a session file is too large?

Large files (≥5000 tokens) are automatically preprocessed with extract-session.sh to compress the data by removing thinking and tool_use blocks.

Does this expose my full file paths?

No. The skill uses ~ prefix in output and never exposes full paths in reports for security.

Full instructions (SKILL.md)

Source of truth, from ai-native-camp/camp-2.

name: history-insight description: This skill should be used when user wants to access, capture, or reference Claude Code session history. Trigger when user says "capture session", "save session history", or references past/current conversation as a source - whether for saving, extracting, summarizing, or reviewing. This includes any mention of "what we discussed", "today's work", "session history", or when user treats the conversation itself as source material (e.g., "from our conversation"). version: 1.1.0 user-invocable: true

History Insight

Claude Code 세션 히스토리를 분석하고 인사이트를 추출합니다.

Data Location

~/.claude/projects/<encoded-cwd>/*.jsonl

Path Encoding: /Users/foo/project → -Users-foo-project

상세 파일 포맷: ${baseDir}/references/session-file-format.md

Execution Algorithm

Step 1: Ask Scope [MANDATORY]

스코프 결정:

명시된 경우 (AskUserQuestion 생략 가능):
- "현재 프로젝트만" / "이 프로젝트" → current_project
- "모든 세션" / "전체" → all_sessions

명시되지 않은 경우 - AskUserQuestion 호출:

question: "세션 검색 범위를 선택하세요"
options:
  - "현재 프로젝트만" → ~/.claude/projects/<encoded-cwd>/*.jsonl
  - "모든 Claude Code 세션" → ~/.claude/projects/**/*.jsonl

Step 2: Find Session Files

# Current project only
find ~/.claude/projects/<encoded-cwd> -name "*.jsonl" -type f

# All sessions (모든 프로젝트)
find ~/.claude/projects -name "*.jsonl" -type f

날짜 필터링: 파일의 mtime(수정시간) 확인 후 필터. OS별 stat 옵션 다름:

macOS: stat -f "%Sm" -t "%Y-%m-%d" <file>
Linux: stat -c "%y" <file>

Step 3: Process Sessions

Decision Tree

Session files found?
├─ No → Error: "No sessions found"
└─ Yes → How many files?
    ├─ 1-3 files → Direct Read + parse
    └─ 4+ files → Batch Extract Pipeline

1-3 Files

직접 Read로 JSONL 파싱. 파일이 크면(≥5000 tokens) extract-session.sh 사용:

${baseDir}/scripts/extract-session.sh <session.jsonl>

4+ Files: Batch Extract Pipeline

캐시 디렉토리 생성 (/tmp/cc-cache/<analysis-name>/)
세션 목록 저장 (sessions.txt)
jq로 메시지 일괄 추출 (user_messages.txt)
정리 및 필터링 (clean_messages.txt)
Task(opus)로 종합 분석

파일이 너무 클 때: 병렬 배치 분석

clean_messages.txt가 너무 커서 Read 실패 시:

파일 분할:

split -l 2000 clean_messages.txt /tmp/cc-cache/<name>/batch_

병렬 Task(opus) 호출:

Task(subagent_type="general-purpose", model="opus", run_in_background=true)
prompt: "batch_XX 파일을 읽고 주제/패턴 요약해줘"

결과 병합: Task(opus)로 종합

Step 4: Report Results

## Session Capture Complete

- **Sessions:** N files processed
- **Messages:** X total, Y after filter

### Extracted Insights
[분석 결과]

Error Handling

Scenario	Response
No session files found	"No session files found for this project."
File too large	Auto-preprocess with extract-session.sh
jq not installed	"Error: jq is required. Install with: brew install jq"
Task failed	"Warning: Could not process [file]. Skipping."
0 relevant sessions	"No sessions matched your criteria."