ldm-session-handoff

ldm-session-handoff is a skill for Claude Code, Codex from Holden323/ldm-skill. It costs 147 tokens per session (1,333 once invoked), scanned A, original, MIT.

A session handoff workflow that saves a conversation, its key decisions, and instructions for restarting it later.

In plain words
What is it for?
It helps export a full transcript, maintain a live routing document with progress and tasks, and create a restart prompt using absolute file paths.
Why use it?
It preserves the original conversation and current status across agent restarts, rather than relying on an imperfect summary.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/likai/Documents/Hermes_Workspace/....

Good fit It helps export a full transcript, maintain a live routing document with progress and tasks, and create a restart prompt using absolute file paths.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ldm-session-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/holden323/ldm-skill/ldm-session-handoff/github.svg)](https://agentmods.dev/skills/holden323/ldm-skill/ldm-session-handoff)
Your own site
<a href="https://agentmods.dev/skills/holden323/ldm-skill/ldm-session-handoff"><img src="https://agentmods.dev/badge/skills/holden323/ldm-skill/ldm-session-handoff/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.

agentmods 80×15 button for ldm-session-handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/holden323/ldm-skill/ldm-session-handoff"><img src="https://agentmods.dev/badge/skills/holden323/ldm-skill/ldm-session-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 147 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,333 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00147 $0.01333
Opus 5 $0.00073 $0.00666
Sonnet 5 $0.00029 $0.00267
Haiku 4.5 $0.00015 $0.00133

Measured today against content hash aedd51ecbfa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ldm-session-handoff scanned grade A with 0 findings 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 today.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/export_jsonl_transcript.py, scripts/export_transcript.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ldm-session-handoff/SKILL.md · 81 lines

What it actually says

会话交接

目标是让下一次会话能核对原始记录,并快速恢复决定、产出、进度和待办。

按用户请求选择产物

  • 完整交接:对话全记录、路由器、重启提示语。
  • 用户明确说“只导出原文”时:只生成对话全记录。
  • 用户明确说“只更新路由器”时:读取现有记录和产出后更新路由器。
  • 用户明确说“只要重启提示语”“不用导出”或“不要创建文件”时:只给提示语;若缺少可靠上下文,明确哪些信息待补。

用户说“加载交接 Skill”“使用交接 Skill”“会话存档”“保存对话”或“准备退出重启”时,默认做完整交接;即使同一句还提到“给我重启提示语”,也不能因此跳过对话全记录和路由器。只有用户用“只”“仅”“不用导出”“不要创建文件”等明确措辞缩小范围时,才改为单项产物。

完整交接流程

  1. 确认当前会话、主题和保存目录。优先使用用户已配置的存档根目录;否则使用当前工作区中的明确目录。
  2. 通过平台原生导出能力或本 Skill 的脚本读取 user/assistant 原文。不要凭记忆生成“全记录”。
  3. 生成路由器,只保留恢复任务需要的决定、产出、进度、待办和新教训。
  4. 核对文件存在、消息数量级合理、来源标记准确。
  5. 报告所有产物的绝对路径,最后直接给出可复制的重启提示语。

格式见 references/formats.md。只有需要选择或排查导出后端时才读 references/export-backends.md

原文真实性

  • “对话全记录”必须来自可核查的会话数据源。
  • 默认保留 user/assistant 可见文本,过滤工具调用、工具输出、推理记录、环境注入和空占位。
  • 不把摘要、路由器或模型回忆标成原文。
  • 导出不完整时写明已获得的范围和“待补存”,不要声称数据必然永久存在。
  • 单条截断会损失原文;只有用户要求控制体积或平台限制无法避免时才截断,并在文件头记录阈值和数量。

路由器

路由器是导航,不复述整段对话。至少写清:

  • 关键决策及其理由。
  • 已完成产物的绝对路径与状态。
  • 正在进行的工作、已做到哪里、下一步是什么。
  • 尚未解决的问题和明确待办。
  • 只有本次新出现且可复用的经验教训。

外部链接只记录需要继续使用的最终入口。敏感凭证不写入路由器。

导出工具

  • Hermes SQLite:scripts/export_transcript.py
  • Claude Code / Codex JSONL:scripts/export_jsonl_transcript.py

脚本只负责导出原文,不负责生成路由器。先用 --list 找到会话,再指定会话和输出路径;本机存在多个后端时不要猜测。

当前活跃会话不会出现在 --list 中。导出步骤:session_search 搜当前对话关键词 → 从结果提取 session_idexport_transcript.py --session <id> --output <绝对路径>。此路径对活跃会话和已结束会话同样有效。

完成检查

  • 交付内容与用户请求的产物范围一致。
  • 全记录文件头写明数据源、会话标识、时间范围、消息数和导出方式。
  • 完整交接时,两个文件均已报告绝对路径,重启提示语已直接发给用户。
  • 失败和截断情况如实标注,没有用摘要冒充原文。

Pitfalls

1. 永远不要声称"导不出来"(2026-09-04/09-08 实战教训)

用户明确要求导出时,不得以"当前活跃session"为由放弃。导出路径:session_search 提取 session_id → export_transcript.py --session <id>。这招对活跃会话和已结束会话都有效。

此错误已导致用户暴怒两次。如果 --list 找不到,换 session_search;如果 session_search 也找不到,如实报告,但先试完两条路再说。

2. 重启提示语和路由器中必须使用绝对路径(2026-09-04/09-08 实战教训)

  • ~/Documents/Hermes_Workspace/...~ 不是绝对路径,用户会暴怒)
  • /Users/likai/Documents/Hermes_Workspace/...

所有文件路径一律用 /Users/likai/ 开头。包括重启提示语、路由器产出清单、用户给的指引。用户已多次纠正此问题。

Files

What ships with it

7 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.

Changes

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.

  1. today Changed · -143 lines · +22 tokens per session aedd51ecbfa4
  2. 9d ago First seen · 224 lines · 125 tokens per session scan A 1d79df5ff1bf

Subscribe to this mod's changes

ldm-session-handoff is a skill published in the GitHub repository Holden323/ldm-skill (31 stars, last pushed yesterday), licensed MIT. It adds 147 tokens to every session and 1,333 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

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.

garrytan/gbrain · 52 tokens

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.…

mem0ai/mem0 · 273 tokens

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…

danielmiessler/LifeOS · 196 tokens

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.

opensquilla/opensquilla · 44 tokens

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…

shiwenwen/hope-agent · 115 tokens

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.

GanyuanRan/Aegis · 45 tokens