Skip to main content
skill CX Codex

long-session-check — Claude Code skill: setup

long-session-check is a Claude Code skill that audits long-session context and memory handling. It starts when constraints get lost or compaction has happened several times.

MIT ★ 741 updated 2026-11-11

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add MiniMax-AI/mcode-stack
/plugin install ronny@mcode-stack
Open on GitHub

What long-session-check does

The long-session-check skill examines how an agent carries work through an extended conversation. It separates disposable tool output from session notes and decisions that should live in project files, then helps choose whether to compact, continue, start fresh, or rewind a bad turn.

Its session mode sorts context into three buckets and records durable material such as decisions, progress, open tasks, acceptance criteria, and long-lived rules. Its design-review mode checks 12 areas, including paired tool calls and results, automatic compaction thresholds, prompt-cache reuse, user-visible history, project memory scope, and memory injection limits.

Claude Code can install it from the marketplace with /plugin marketplace add MiniMax-AI/mcode-stack, followed by /plugin install ronny@mcode-stack. The skill also names a project progress or design document and handoff-doc as places for saved work.

What it helps with

  • sort a long conversation into disposable, resumable, and durable context
  • record decisions and open work for a later session
  • choose whether to compact, restart, or rewind the current task
  • audit an agent's memory and compaction design

Example prompts for the agent

  • Check this session and sort its context into what to drop, summarize, and write to a file.
  • Review the agent design against all 12 checks and return pass, fail, unknown, evidence, and priority fixes.
  • Several compactions caused drift. Create a hand-off document and state the next move.

How to install long-session-check

1Plugin marketplace

/plugin marketplace add MiniMax-AI/mcode-stack
/plugin install ronny@mcode-stack

This installs the whole ronny plugin with all its skills

2Skills CLI (Vercel)

npx skills add MiniMax-AI/mcode-stack --skill long-session-check -a claude-code

3Manually: put the files in place

~/.claude/skills/long-session-check/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/long-session-check/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about long-session-check

How do I install long-session-check in Claude Code?

Add the marketplace with /plugin marketplace add MiniMax-AI/mcode-stack, then install the skill with /plugin install ronny@mcode-stack.

What does long-session-check do?

It examines long-session handling: tool-result clearing, context compaction, file-based decisions, and memory scope. It also structures the next step after compaction, drift, or a wrong turn.

What does long-session-check need to work?

It runs in the listed coding-agent platforms and can write durable session material to a project progress or design document, or through handoff-doc.

Source text

SKILL.md · MIT
---
name: long-session-check
description: Check how an agent or a working session handles long conversations, covering tool-result clearing, compaction, what gets written to files, when to start a new session, and how memory is scoped. Use when a long session starts forgetting constraints, after several compactions, or when reviewing an agent's compaction and memory design.
---

# Long Session Check

The context window is a workbench, not a warehouse. Compaction answers "it
does not fit right now"; memory answers "will we remember next time". Both are
lossy. The safe pattern is to get anything important into human-readable
files early, and to treat compaction as tidying the workbench, not as the only
safety net.

Companion to MCode Engineering Notes 03, "Keeping long sessions sharp".
Plain-text checklist: `checklists/long-session.md`.

This skill has two modes. Pick the one that matches the request.

## Mode A - the session you are in right now

1. **Sort what is in context into three bins.**
   - *Drop*: things you can fetch again or no longer need (large file reads,
     test logs, search results, abandoned attempts).
   - *Summarize*: this-session-only story (where we are, next step, open bugs
     and leads, files recently touched).
   - *Write to a file*: anything that would hurt if lost or is needed in a
     later session (decisions and their reasons, progress, todos, acceptance
     criteria, long-lived rules).
2. **Write the third bin down now**, in the project's progress or design doc,
   or via `handoff-doc`.
3. **Choose the next move:**
   - Same task, history just long: compact, and say what comes next and what
     must be kept (for example "focus on the auth refactor, drop the test
     debugging").
   - New task: start a new session.
   - Compacted several times and drifting, or repeating questions already
     answered, or breaking earlier constraints: write a hand-off doc and start
     fresh with it.
   - Went the wrong way: rewind to before the mistake instead of compacting,
     so the wrong attempt does not end up in the summary.

## Mode B - reviewing an agent's design

Read the agent's code and configuration and answer each item with evidence
(file and line, config key, or observed behaviour):

1. Are old tool results cleared before resorting to a full summary?
2. Are tool calls and their results kept in pairs when results are cleared?
   Many model APIs reject orphaned calls.
3. Do key decisions and constraints get written to files, not only kept in
   the conversation?
4. Does manual compaction accept instructions about what to keep and what
   comes next?
5. Does automatic compaction trigger early enough to leave room for output
   and for the summary itself? Can the session continue if compaction fails
   (quota, smaller model)?
6. Can the compaction request reuse the prompt cache? Does compaction run so
   often that it keeps invalidating the cache?
7. Does compaction change only what the model sees, leaving the user's visible
   history intact? Is it kept out of user-facing budgets such as step limits?
8. Is the model told that context is managed automatically, so it does not
   stop half way to "continue next turn"?
9. Is project memory (`AGENTS.md` or similar) short and limited to stable
   rules?
10. Is memory scoped (session, project, user)? Are temporary progress and
    todos kept out of long-term memory?
11. When memory exceeds its injection budget, is truncation visible, and are
    the most important rules guaranteed to load?
12. Can a human open, edit and switch off the memory? Rules that must be
    enforced belong in hooks, not in memory.

## Output

For Mode A: the three bins, what you wrote to which file, and the chosen next
move. For Mode B: a table of the items with pass / fail / unknown, the
evidence, and the top fixes in priority order.

© Ronny (MiniMax Code team) · MIT · MiniMax-AI/mcode-stack

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set27

The whole set →
evidence-first-review evidence-first-review is a Claude Code skill that audits an agent’s finished work from command logs and test evidence. It runs before a PR merge or an analysis is accepted. CX Codex +1 ★ 741repo stars pr-description pr-description is a Claude Code skill that drafts and verifies pull request descriptions for GitHub and GitLab. It runs when opening a PR or when MCode Review reports missing sections. CX Codex +1 ★ 741repo stars subagent-split-check subagent-split-check is a Claude Code skill that decides whether work belongs in a subagent or the main loop. It checks context boundaries before a split. CX Codex +1 ★ 741repo stars context-tax-audit The context-tax-audit skill for Claude Code inventories injected data in agent requests to reduce token usage. It identifies redundant prompt blocks and configurations that hinder prompt cache performance. CX Codex +1 ★ 741repo stars long-command-check long-command-check is a Claude Code skill that audits shell command execution in agent harnesses. It checks dev server hangs, timeouts, backgrounding, and prompt cache expiration. CX Codex +1 ★ 741repo stars tool-budget-audit tool-budget-audit is a Claude Code skill that measures context used by tool schemas and call results. It flags catalog bloat and mistaken tool choices. CX Codex +1 ★ 741repo stars pr-quiz pr-quiz is a Claude Code skill that drafts multiple-choice questions for PR authors. It triggers when the MCode Review pipeline requests an author quiz. CX Codex +1 ★ 741repo stars pr-review pr-review is a Claude Code skill that reviews pull requests and branches with MCode Review rules. It runs from CI or on a developer’s request before human review. CX Codex +1 ★ 741repo stars

Project sponsors

Companies that keep this analytics open