Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/chamherry/claude-code-third-party-plugins/continue-sessiongit clone --depth 1 https://github.com/ChamHerry/claude-code-third-party-pluginsWhat 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 | $0.00008 | $0.05559 |
| Opus 5 | $0.00004 | $0.02780 |
| Sonnet 5 | $0.00002 | $0.01112 |
| Haiku 4.5 | $0.00001 | $0.00556 |
Grade B, and why
continue-session scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/session-exports/{timestamp}-{uuid}.md How it starts
The opening of the file, as written. The whole thing — 858 lines — stays where its author put it; the contents beside it link to each section on GitHub.
智能搜索已保存的会话,支持按项目、时间、关键词过滤,选择后生成 Markdown 格式的会话摘要供在新会话中继续工作。
核心特性:
- 🔍 智能搜索: 支持按项目、时间范围、关键词搜索
- 📋 可视化列表: 清晰展示会话信息(标题、时间、进度)
- 📝 完整导出: 生成包含进度、方案、决策的 Markdown 文档
- 💡 行动建议: 自动生成后续工作建议
执行步骤
1. 扫描已保存的会话
a. 检查存储目录是否存在(项目本地)
SUMMARY_BASE="./.claude-sessions/summaries"
if [ ! -d "$SUMMARY_BASE" ]; then
echo "❌ 错误:未找到已保存的会话"
echo "提示:使用 /session-manager:save 保存当前会话"
echo "📁 会话将保存在项目目录: ./.claude-sessions/"
exit 1
fi
b. 查找所有摘要文件(项目本地)
# 查找当前项目的所有会话摘要
find "$SUMMARY_BASE" -maxdepth 2 -name "summary.json" -type f
c. 读取并解析所有摘要文件
- 使用 Read 工具读取每个 summary.json
- 提取关键信息用于展示:
- 会话标题
- 项目名称
- 保存时间
- 进度信息(已完成/总数)
- 会话 ID 和存储路径
d. 按保存时间排序(最新的在前)
# 使用 Python 脚本读取和排序
python3 << 'EOF'
import json
import glob
import os
from datetime import datetime
summary_files = glob.glob(os.path.expanduser("~/.claude/session-summary/**/summary.json"), recursive=True)
sessions = []
for file_path in summary_files:
with open(file_path, 'r', encoding='utf-8') as f:
data = json.load(f)
data['_file_path'] = file_path
sessions.append(data)
# 按 savedAt 时间排序
sessions.sort(key=lambda x: x.get('savedAt', ''), reverse=True)
# 输出 JSON
print(json.dumps(sessions, ensure_ascii=False))
EOF
2. 首次展示(最近 10 个)
a. 提取最近 10 个会话信息
b. 格式化展示选项
每个选项格式:
label: "[时间] 项目名 - 会话标题"
description: "进度:X/Y 已完成 | 文件变更:Z 个"
c. 使用 AskUserQuestion 展示列表
question: "选择要继续的会话(显示最近 10 个):"
header: "会话列表"
multiSelect: false
options:
- label: "🔍 搜索和过滤"
description: "按项目、时间或关键词搜索会话"
- label: "[2025-11-03 16:00] claude-code-init - 添加会话管理插件"
description: "进度:4/6 已完成 | 文件变更:3 个"
- label: "[2025-11-03 14:30] my-project - 实现用户认证"
description: "进度:5/8 已完成 | 文件变更:12 个"
... (最多 10 个)
- label: "📚 查看更多..."
description: "显示更多会话(第 11-20 个)"
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.
- 2d ago First seen · 858 lines · 8 tokens per session scan B 16cd433b9c48
continue-session is a command published in the GitHub repository ChamHerry/claude-code-third-party-plugins (50 stars, last pushed 9mo ago), licensed MIT. It adds 8 tokens to every session and 5,559 once invoked, about $0.0000 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.