AGENT SKILL

claude-code-sessions

Search, analyze, and manage Claude Code session history. Use when the user wants to find past sessions, check token usage, review tool breakdowns, resume previous work, or manage tasks across sessions. Provides 11 skills and a web dashboard.

适用职业开发工程师
License 许可
MIT
最近更新
2026-11-13
Stars
★ 3.3w
Forks
3.9k

01 前言 Front Matter

name
claude-code-sessions
description
Search, analyze, and manage Claude Code session history. Use when the user wants to find past sessions, check token usage, review tool breakdowns, resume previous work, or manage tasks across sessions. Provides 11 skills and a web dashboard.

03 SKILL.md 正文

Claude Code Sessions

Session intelligence plugin for Claude Code. Reads the JSONL session files that Claude Code writes to ~/.claude/projects/ and makes them searchable and analyzable.

What It Does

Claude Code records every session as a JSONL file — messages, tool calls, token counts, diffs, tasks. This plugin reads those files and provides two interfaces. Most operations are read-only; delete and cleanup skills can remove session files when explicitly invoked.

11 skills usable directly in Claude Code:

Skill Purpose
/session-search "query" Full-text search across every session
/session-stats Token usage, model distribution, tool breakdown
/session-list List sessions sorted by recency, size, or duration
/session-detail Deep dive into a specific session
/session-diff Compare two sessions — files, tools, topics
/session-timeline Chronological view of sessions on a project
/session-resume Generate a context recovery prompt from any session
/session-tasks Find pending and orphaned tasks across sessions
/session-export Export a session as clean markdown
/session-cleanup Find empty, tiny, or stale sessions
/session-delete Delete sessions and their associated tasks

Web dashboard at localhost:3000 with four views: Dashboard (summary stats), Sessions (sortable table with bulk operations), Search (full-text with context snippets), Tasks (grouped by status with orphan detection).

Install

/plugin marketplace add apappascs/claude-code-sessions
/plugin install claude-code-sessions@claude-code-sessions

No API keys. No config. No runtime dependencies. It reads what's already on disk.

For the dashboard:

bun run ui
# → http://localhost:3000

Architecture

Same TypeScript modules power skills, dashboard, and CLI:

lib/formatters.ts      — pure utilities, no I/O
lib/session-parser.ts  — parses one JSONL file into structured data
lib/session-store.ts   — scans all sessions, aggregates, searches
ui/server.ts           — HTTP endpoints + static file serving

Each lib file doubles as a standalone CLI:

bun run lib/session-store.ts list --sort recency --limit 10
bun run lib/session-store.ts search "database migration" --since 2025-01-01
bun run lib/session-parser.ts stats path/to/session.jsonl

Use Cases

  • Find the session where you solved a specific problem weeks ago
  • See which projects consume the most tokens
  • Track pending tasks across all sessions and projects
  • Resume a past session with full context
  • Compare how two sessions approached the same problem
  • Export session transcripts for documentation

Links

04 同仓库更多 Skills

davila7
davila7/claude-code-templates

wealthville-pool-scoring

Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter/Hold/Exit/Reduce/Avoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.

Skill与智能体开发
★ 3.3w
davila7
davila7/claude-code-templates

technical-debt-auditor

Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO/FIXME/HACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like "where should I focus refactoring", "find code smells", "audit my codebase", "what technical debt do we have", "prioritize cleanup work", or asks about code quality metrics. Also trigger when the user mentions "code rot", "legacy cleanup", "refactoring priorities", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say "technical debt" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.

Skill与智能体开发
★ 3.3w
davila7
davila7/claude-code-templates

readonly-sql-guard

Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production/ERP/analytics database (a "query" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write/DDL/side-effect/transaction-escape risks. Checks what a statement CALLS, not just its shape.

数据分析师后端与接口Skill与智能体开发
★ 3.3w
davila7
davila7/claude-code-templates

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

前端开发
★ 3.3w
davila7
davila7/claude-code-templates

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

测试与质量前端开发
★ 3.3w
davila7
davila7/claude-code-templates

discernment-nudge

After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.

内容创作者写作与文案Skill与智能体开发
★ 3.3w