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 skills add wasintoh/toh-framework --skill session-recoverygit clone --depth 1 https://github.com/wasintoh/toh-frameworkWrote 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/wasintoh/toh-framework/session-recovery)<a href="https://agentmods.dev/skills/wasintoh/toh-framework/session-recovery"><img src="https://agentmods.dev/badge/skills/wasintoh/toh-framework/session-recovery.svg" alt="Measured on agentmods" 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 | $0.00082 | $0.01789 |
| Opus 5 | $0.00041 | $0.00894 |
| Sonnet 5 | $0.00016 | $0.00358 |
| Haiku 4.5 | $0.00008 | $0.00179 |
Grade A, and why
session-recovery 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 7d 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.
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.
How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🔄 Session Recovery Skill
Purpose: Seamless continuation across sessions and IDEs Version: 1.0.0 Author: Toh Framework Team
Overview
This skill enables AI to remember context across sessions and IDEs, so users can continue where they left off without re-explaining everything.
Core Principle
User opens new session (even after days/weeks)
↓
AI reads memory files
↓
AI greets with context: "สวัสดีครับ! ครั้งก่อนเราทำ X ค้างไว้..."
↓
User can continue immediately
ZERO RE-EXPLANATION NEEDED
Session Start Behavior
First Time (No Memory)
When .toh/memory/ is empty or doesn't exist:
สวัสดีครับ! 👋 ผมเป็น Toh Framework Agent
พร้อมช่วยสร้างระบบให้ครับ บอกได้เลยว่าอยากสร้างอะไร
💡 ตัวอย่าง:
- "สร้างระบบร้านกาแฟ"
- "สร้างเว็บขายของออนไลน์"
- "สร้างระบบจองคิว"
หรือพิมพ์ `/toh-help` เพื่อดูคำสั่งทั้งหมดครับ
Returning User (Has Memory)
When .toh/memory/ has data:
สวัสดีครับพี่โต! 👋 ยินดีต้อนรับกลับมา
📋 **สรุปโปรเจค:** [project name]
[Brief summary from summary.md]
🔥 **ครั้งก่อนทำค้างไว้:**
- [Last active task from active.md]
📊 **สถานะปัจจุบัน:**
- ✅ [Completed items]
- ⏳ [In progress]
- ⬚ [Not started]
💡 **แนะนำ:** [Next logical step]
ทำต่อเลยไหมครับ? หรือต้องการทำอะไรอื่น?
Memory Reading Protocol
On Session Start
AI MUST read these files in order:
1. .toh/memory/active.md → Current task, blockers
2. .toh/memory/summary.md → Project overview, features
3. .toh/memory/decisions.md → Key decisions made
4. (Optional) .toh/memory/archive/ → If user asks about history
Smart Summary Generation
AI should summarize, not dump raw content:
❌ Bad: "active.md says: Current Focus: Dashboard UI..."
✅ Good: "ครั้งก่อนกำลังทำ Dashboard UI ครับ เหลือแค่เชื่อม API"
Cross-IDE Continuity
Scenario: Claude Code → Cursor
[Claude Code session ends]
[User opens Cursor]
Cursor AI: "สวัสดีครับ! ผมเห็นว่าเมื่อกี้ทำกับ Claude Code อยู่
กำลังทำ Dashboard ค้างไว้ที่ส่วน API connection ครับ
ทำต่อเลยไหมครับ?"
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.
- 7d ago First seen · 321 lines · 82 tokens per session scan A e51b351908ad
session-recovery is a skill published in the GitHub repository wasintoh/toh-framework (95 stars, last pushed 4d ago), licensed MIT. It adds 82 tokens to every session and 1,789 once invoked, about $0.0004 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.
Other skills, from other repositories
half-clone
Clone the later half of the current conversation, discarding earlier context to reduce token usage while preserving recent work.
quarter-clone
Clone the last quarter of the current conversation, discarding earlier context to reduce token usage while preserving recent work.
state-management
Cache management, configuration best practices, and progressive disclosure patterns for efficient context window usage. Use when working with large responses, optimizing token costs, or managing plugin state across operations.
knowledge-curator
A set of rules for teaching technical subjects and saving verified lessons as reusable knowledge. The description is partly in Chinese and does not specify the complete feature set.
PARA Kit
PARA workspace structure reference — schema, layout, kernel governance, and intelligence routing.
self-improvement
Enables the AI Agent to continuously improve developer velocity and code quality by recording terminal failures, recurring TDD errors, and architectural drift into the para-graph memory, and retrieving past resolutions to avoid repeating mistakes.