mk:session-continuation

mk:session-continuation is a skill for Claude Code, Codex from ngocsangyem/MeowKit. It costs 47 tokens per session (647 once invoked), scanned A, original, MIT.

A workflow-state tool that saves unfinished work and restores it later, including after a conversation reaches its context limit.

In plain words
What is it for?
It helps with handoffs, pausing and resuming workflows, saving state, and continuing incomplete tasks.
Why use it?
It prevents progress and working state from being lost when a session ends or needs to continue in a new session.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/ngocsangyem/meowkit/session-continuation
Any agent
npx skills add ngocsangyem/MeowKit --skill session-continuation
Clone the repo
git clone --depth 1 https://github.com/ngocsangyem/MeowKit

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 mk:session-continuation

README.md
[![agentmods](https://agentmods.dev/badge/skills/ngocsangyem/meowkit/session-continuation.svg)](https://agentmods.dev/skills/ngocsangyem/meowkit/session-continuation)
Your own site
<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/session-continuation"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/session-continuation.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 647 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00047 $0.00647
Opus 5 $0.00023 $0.00324
Sonnet 5 $0.00009 $0.00129
Haiku 4.5 $0.00005 $0.00065

Measured yesterday against content hash 86b96396451b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mk:session-continuation 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 yesterday.

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.

.claude/skills/session-continuation/SKILL.md · 76 lines

What it actually says

Session Continuation

Manage workflow state across sessions with handoff and resume.

When to Use

  • Runtime reports that the session is approaching its context-warning threshold
  • User says "handoff", "save", "pause"
  • User says "resume" + workflow ID
  • Session ending with incomplete workflow
  • Incomplete workflow from previous session

Plan State Variables

state_vars[4]{var,purpose,persistence}:
  MEOWKIT_ACTIVE_PLAN,Current active plan path,Session temp file
  MEOWKIT_SUGGESTED_PLAN,Branch-matched plan hint,Inferred from git branch
  MEOWKIT_COMPLEXITY,Auto-detected task complexity,Session memory
  MEOWKIT_ACTIVE_AGENTS,Currently active agents,Session memory

Process

  1. Detect trigger — token limit, user command, or session ending
  2. If handoff — load references/handoff-flow.md, execute save + summary
  3. If resume — load references/resume-and-state.md, execute load + restore + continue
  4. If list — show all saved workflows from .claude/logs/workflows/

References

Reference When to load Content
handoff-flow.md On handoff/save trigger State save format, summary generation
resume-and-state.md On resume trigger Resume steps, state management, error handling, TOON format

Quick Commands

workflow:handoff           → Save state + get resume instructions
workflow:resume AUTH-123   → Load state + continue from last phase
workflow:list              → Show all saved workflows

Gotchas

  • Stale handoff after codebase changes: Saved state references files that were renamed or deleted → Validate all file paths in handoff state before resuming
  • TOON corruption on concurrent sessions: Two agents writing state simultaneously → Use file locking or session-scoped state files
Files

What ships with it

2 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. yesterday First seen · 76 lines · 47 tokens per session scan A 86b96396451b

Subscribe to this mod's changes

mk:session-continuation is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 647 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

company-brain

Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki…

coreyhaines31/makerskills · 322 tokens

second-brain

When you want to capture into, compile, query, lint, or connect your personal Second Brain. Wraps the Karpathy LLM Wiki schema (Obsidian or any markdown vault) — raw/ (unprocessed sources), wiki/ (AI-compiled interlinked topic pages), outputs/ (generated artifacts). Tool-agnostic in design but defaults to a vault at…

coreyhaines31/makerskills · 238 tokens

learn-from-fix

Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.

oliver-kriska/claude-elixir-phoenix · 46 tokens

self-improve

Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…

tobihagemann/turbo · 125 tokens

compound-docs

Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.

oliver-kriska/claude-elixir-phoenix · 38 tokens

claude-md-updater

Scans the session for lessons and workflows, then proposes scoped CLAUDE.md edits. Use for save this lesson or add to context.

jamditis/claude-skills-journalism · 34 tokens