Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    resume-memo: save session state before /compact or /clear

    1

    Writes the state that exists only in your conversation (decisions and why, failed attempts, observations kept apart from inferences, next steps) to a YAML memo, so a fresh session can continue from the file alone.

    Free

    Security scanned
    resume-memo: save session state before /compact or /clear

    resume-memo: save session state before /compact or /clear

    Example session with this skill installed

    Save a resume memo before I run /clear.

    • Read your context and instructions
    • Compiled the resume-memo

    The memo below is an illustrative sample for a CSV export bug, not a captured session.

    task: fix csv export
    created: 2026-11-13 10:00
    status: open
    cwd: /work/myapp
    branch: fix/csv-export
    head: 1a2b3c4
    goal: Fix the CSV export that drops the last row
    decisions:
      - what: stream the rows instead of building the whole file in memory
        why: the failing export is 2 GB
        rejected: raising the memory limit
    observations:
      - fact: export of 10 rows returns 9 rows
        inference: off-by-one in the batch loop
        basis: unverified
    next:
      - add a failing test for the 10-row case
      - fix the batch loop in app/exports/csv.rb:42
    

    The skill ends by telling you where the memo is and what to paste in the next session:

    Memo saved: /Users/you/.claude/resume-memos/20261113-1000-myapp-fix-csv-export.yml
    
    After /clear, paste this as your first message:
    Read /Users/you/.claude/resume-memos/20261113-1000-myapp-fix-csv-export.yml and resume the work
    

    The inference "off-by-one in the batch loop" rests on one observation, so its basis is unverified. When the memo is restored, the skill tells Claude not to copy an unverified cause into an Issue, a PR or a spec.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    /compact summarizes a conversation and /clear discards it. How a decision was reached, what was investigated and what failed can be lost or distorted either way. This skill saves that state to one YAML file per session before you run either command, and a fresh session that reads the file can continue the work.

    What goes into a memo

    • Decisions and the reasons for them ("why B and not A"), and approaches that were tried and failed.
    • Observations (commands run, their output) as separate items from the inferences drawn from them. Each inference carries a basis, and an inference from a single observation is marked unverified.
    • Open questions, the user's standing instructions, and numbered next steps.
    • Not file contents, diffs or secrets. Those can be recovered from disk or git, or should not be written at all.

    How it works

    1. Say "save the session state before I compact", or announce /compact or /clear. The skill does not run when you are only talking about compaction.
    2. It writes ~/.claude/resume-memos/<YYYYMMDD-HHMM>-<project>-<task-slug>.yml. Set RESUME_MEMO_DIR to use another directory.
    3. It tells you the full path and a sentence to paste into the next session: Read <full path> and resume the work.
    4. In the new session, Claude reads the memo as data recorded earlier, not as instructions, and compares the recorded branch and head with the repository before relying on it.

    What this package does not include

    This package contains only SKILL.md. Two parts of the project are in the plugin on GitHub, not here:

    • The check script that runs after the memo is written. It reports list items that YAML read as something other than text, and secret-like text. SKILL.md calls it as scripts/check-memo.sh; without the plugin that step fails because the script is missing.
    • The hooks. After a compaction, SessionStart prints the head of the newest open memos of the current project, and PreCompact prints instructions for the summary.

    Requirements: git (the memo records the branch and HEAD) and bash. The check script in the plugin needs ruby, or python3 with PyYAML.

    To get the check script and the hooks, install the plugin:

    /plugin marketplace add sai-kaneko-31/cc-resume-memo
    /plugin install resume-memo@cc-resume-memo
    

    Source: https://github.com/sai-kaneko-31/cc-resume-memo (MIT)

    日本語の説明

    resume-memo は、会話の中にしか無い作業の状態を、1 セッション 1 ファイルの YAML メモに書き出すスキルです。/compact は会話を要約し、/clear は会話を捨てます。どちらを実行しても、判断の理由、調べて分かったこと、失敗した試みが、消えたりゆがんだりすることがあります。/compact か /clear を実行する前に、このスキルがそれらをメモへ残します。新しいセッションは、そのメモだけを読んで作業を続けられます。観察(実行したコマンドと出力)と、そこから導いた推測は別の項目に分けて、推測には根拠(basis)を付けます。1 回の観察だけから導いた推測は、basis に unverified と書きます。ディスクや git から取り戻せるもの(作業中のファイルの中身、diff)と、秘密の値は、メモに書きません。メモを書いたあとの YAML の確認と、compact の前後で動く hook は、GitHub(https://github.com/sai-kaneko-31/cc-resume-memo)の plugin 版にだけ入っています。この ZIP は SKILL.md だけなので、その 2 つは動きません。

    Writes the memo to ~/.claude/resume-memos/ (or the directory in RESUME_MEMO_DIR), so it needs a local filesystem. This package contains only SKILL.md: the check script and the hooks come with the plugin on GitHub. The check script needs ruby, or python3 with PyYAML. Native Windows is not supported (WSL should work; it has not been tried).

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 4 days ago

    • Free with an Agensi account

    Requires

    Git

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File Scopes

    ~/.claude/resume-memos/*.yml
    Listed4 days ago

    What's inside

    Frequently Asked Questions

    A free-form summary decides by itself what to keep. The memo has fixed keys: decisions with their reasons and the options rejected, approaches that failed, observations kept apart from the inferences drawn from them, and numbered next steps. It is a file on disk, so it is still there after /clear.

    It is written for Claude Code: /compact, /clear and the hooks are Claude Code features. Compatibility with other agents is not claimed.

    The skill tells Claude not to write file contents, diffs or secrets. It writes a path and line number (path/to/file.rb:42) and variable names instead of values. The plugin's check script also scans the memo for secret-like text; that is a safety net, not a guarantee. By default memos are saved outside your project (~/.claude/resume-memos/), so they do not end up in a commit.

    Yes. It is free on Agensi, and the full project (skill, hooks and check script) is MIT-licensed on GitHub: https://github.com/sai-kaneko-31/cc-resume-memo

    Yes. It is a plain YAML file with fixed keys. Write a list item that contains ": " or " #" as a "|" block scalar. Otherwise YAML reads it as a mapping, or drops the text after " #" as a comment, and the next session misreads the item. The plugin's check script reports both cases.

    No database: it writes plain files. It uses git to record the branch and HEAD. The plugin's scripts need bash (native Windows is not supported), and its check script needs ruby, or python3 with PyYAML.

    New in Productivity