Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add team-attention/plugins-for-claude-natives/plugin install session-wrapWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/team-attention/plugins-for-claude-natives/history-insight)<a href="https://agentmods.dev/skills/team-attention/plugins-for-claude-natives/history-insight"><img src="https://agentmods.dev/badge/skills/team-attention/plugins-for-claude-natives/history-insight/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/team-attention/plugins-for-claude-natives/history-insight"><img src="https://agentmods.dev/badge/skills/team-attention/plugins-for-claude-natives/history-insight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00096 | $0.01025 |
| Opus 5 | $0.00048 | $0.00513 |
| Sonnet 5 | $0.00019 | $0.00205 |
| Haiku 4.5 | $0.00010 | $0.00103 |
Grade B, and why
history-insight scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find ~/.claude/projects/<encoded-cwd> -name "*.jsonl" -type f How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
- "현재 프로젝트만" / "이 프로젝트" →
-
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]
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 144 lines · 96 tokens per session scan B c31b5bf8c0a3
history-insight is a skill published in the GitHub repository team-attention/plugins-for-claude-natives (824 stars, last pushed 4mo ago), licensed MIT. It adds 96 tokens to every session and 1,025 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.