session-replay
Skill1 starsChanged 7 months agoMITView on GitHub
lc 会话回放器——把 journal/rollout/决策流三源聚合为 agentplay/v1 兼容时间线 + 本地 HTML 视图（零外发零依赖）。用于复盘、失败路径分析、决策点审计。
3 other projects use a version of this.
Adopted by
Most recently taken up by
- calube/mobile-observabilitytheir own version, first seen Oct 9, 2026
- issue-orchestrator/issue-orchestratortheir own version, first seen Sep 6, 2026
- JDerekLomas/claude-code-skillstheir own version, first seen Jan 14, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- calube/mobile-observability★ 116same name
- issue-orchestrator/issue-orchestrator★ 10same name
- JDerekLomas/claude-code-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- depth-four-questionsSkill
- feishu-doc-authoringSkill
- lc-gov-playbookSkill
The file
Files
Session Replay（lc 最小回放器）
借鉴 AgentPlay 的脱敏 schema（不借其运行时——lc 会话布局与 Claude Code/Codex 不同）。peer-borrow 实证：2026-10-29 五方评审第 1 批④。
用法
# 导出会话时间线（JSON）+ 本地 HTML 视图
python3 scripts/session_map.py --session <session_id>
# 脱敏模式：不含 tool_result 预览文本（外发/分享前必用）
python3 scripts/session_map.py --session <id> --redact
# 仅导出 HTML
python3 scripts/session_map.py --session <id> --html out/replay.html数据源（三源聚合）
| 源 | 提供 | 键 |
data/journals/<session>.jsonl | tool_call/tool_result 事件（tool_call_id 配对 call↔result） | session_id = 文件名 |
~/.lingclaude/rollouts/*.jsonl | token 曲线（turn_end 累计） | 陷阱：文件名是 thread_id，session_id 在首行 session_meta |
data/arch_ledger/decisions_YYYYMM.jsonl | 决策点（domain/confidence/kind） | session_id 字段 |
契约（单测钉住）
- 幂等：journal 行数水位，无新增行时短路不重写（不是截断式假幂等）
- 确定性：同输入两次导出逐字节一致
- 脱敏：
--redact时输出零 prompt/result 原文（schema 要求） - 决策↔工具反查：decisions 的
tool_call_id可 join journal 事件
验收惯例（⑪d）
新增 CLI 工具应成对交付 skill 文档（可发现性），本 skill 即范例。反向：skill 描述的能力必须有真实 CLI/模块支撑，禁止只写文档不落码。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.