Memori Long-Term Memory
MemoriLabs/Memori
Connects Claude Code to Memori Cloud for long-term memory, recalling stored context before substantive replies and saving new context afterward.
Sweeps a conversation before compaction and saves durable facts, decisions and session records into the Compartment encrypted memory vault as short one-claim memories.
Install Compartment Session Sweep
$ npx skills add MaxFreedomPollard/Compartment --skill compartmentalize -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install MaxFreedomPollard/Compartment compartmentalize --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/MaxFreedomPollard/Compartment.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/compartmentalize .claude/skills/compartmentalize && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "compartmentalize" agent skill from https://github.com/MaxFreedomPollard/Compartment/tree/main/skills/compartmentalize into .claude/skills/compartmentalize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compartmentalize", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/MaxFreedomPollard/Compartment/tree/main/skills/compartmentalizeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add MaxFreedomPollard/Compartment --skill compartmentalize -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install MaxFreedomPollard/Compartment compartmentalize --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MaxFreedomPollard/Compartment.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/compartmentalize .agents/skills/compartmentalize && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "compartmentalize" agent skill from https://github.com/MaxFreedomPollard/Compartment/tree/main/skills/compartmentalize into .agents/skills/compartmentalize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compartmentalize", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MaxFreedomPollard/Compartment --skill compartmentalize -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install MaxFreedomPollard/Compartment compartmentalize --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MaxFreedomPollard/Compartment.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/compartmentalize .cursor/skills/compartmentalize && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "compartmentalize" agent skill from https://github.com/MaxFreedomPollard/Compartment/tree/main/skills/compartmentalize into .cursor/skills/compartmentalize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compartmentalize", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/MaxFreedomPollard/Compartment.git --path skills/compartmentalize--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add MaxFreedomPollard/Compartment --skill compartmentalize -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install MaxFreedomPollard/Compartment compartmentalize --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MaxFreedomPollard/Compartment.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/compartmentalize .gemini/skills/compartmentalize && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "compartmentalize" agent skill from https://github.com/MaxFreedomPollard/Compartment/tree/main/skills/compartmentalize into .gemini/skills/compartmentalize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compartmentalize", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install MaxFreedomPollard/Compartment compartmentalizeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add MaxFreedomPollard/Compartment --skill compartmentalize -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/MaxFreedomPollard/Compartment.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/compartmentalize .github/skills/compartmentalize && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "compartmentalize" agent skill from https://github.com/MaxFreedomPollard/Compartment/tree/main/skills/compartmentalize into .github/skills/compartmentalize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compartmentalize", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MaxFreedomPollard/Compartment --skill compartmentalize -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install MaxFreedomPollard/Compartment compartmentalize --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MaxFreedomPollard/Compartment.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/compartmentalize .opencode/skills/compartmentalize && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "compartmentalize" agent skill from https://github.com/MaxFreedomPollard/Compartment/tree/main/skills/compartmentalize into .opencode/skills/compartmentalize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compartmentalize", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
compartmentalize- GitHub stars
- 578
- Token cost
- ~750 tokens
- SKILL.md length
- 397 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Sweeps a conversation before compaction and saves durable facts, decisions and session records into the Compartment encrypted memory vault as short one-claim memories.
- Saving what matters from a long session before it is compacted
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Banking a finished piece of work into persistent memory
- Recording decisions, contacts and file locations for later sessions
What it does
The skill is meant to run before compacting or summarizing, or at any point to bank a session. It scans the whole conversation, including parts already summarized, and stores what is worth reusing: names and contacts, addresses, account IDs, lasting file locations and configuration, preferences, URLs and hostnames, durable decisions, and credentials together with where they live. Transient chatter, one-off trivia, public information, in-progress run results, logs and temporary paths are skipped, as is the vault passphrase itself.
For each item the agent searches memory first, then updates an existing memory or stores a new one. It also stores the session itself as several separate claims: what was asked, what it became, what changed and what is still open. Each memory stands alone as one claim of at most 200 characters by default, with no pronouns pointing back at the conversation. Several facts go in one batch call, preferences are stored as opinions that supersede older ones, and namespace, tags, importance and a discovered date are set, while the vault stamps dates itself.
When your agent uses it
- Saving what matters from a long session before it is compacted
- Banking a finished piece of work into persistent memory
- Recording decisions, contacts and file locations for later sessions
Example prompts
- “Compartmentalize this session before we compact.”
- “Save the decisions and open items from today's work into memory.”
- “Sweep our conversation and store anything we will need again, but skip the debugging noise.”
Requirements
- Compartment, the encrypted memory vault, with its MCP memory tools
What it can do on your machine
Read from SKILL.md and the folder at commit 43b5ccc. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Compartment Session Sweep loads about 750 tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 397 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from MaxFreedomPollard/Compartment at commit 43b5ccc, republished under its Apache-2.0 licence (© MaxFreedomPollard). 397 words, ~750 tokens.
Download SKILL.mdSave it as
.claude/skills/compartmentalize/SKILL.md (or your agent's skills folder).- name
- compartmentalize
- description
- Sweep this conversation and save everything worth referencing again in future work into Compartment, the encrypted memory vault. Run it before compacting or summarizing so nothing is lost to the summary, or on its own at any point to bank the session.
- metadata.tags
- memory, compartment, context, session, recall
- metadata.version
- 1.0.0
- metadata.platforms
- macos, linux, windows
Save to Compartment before compacting.
Sweep the entire conversation, including any part already summarized, and store to Compartment what it holds that is worth keeping.
STORE anything worth referencing again in future work: names, addresses, contacts, account IDs, passwords, API keys and other credentials, lasting file locations and configuration, preferences, and every durable fact or decision reached. Not transient chatter, one-off trivia, things freely available on the internet, or the working details of a task in progress, such as run results, errors, log contents and temporary paths or settings.
For each item, memory_search first, then memory_store: update the existing
memory when one already covers it, create a new one when none does.
Always store, when present: people, contacts and addresses. Passwords, API keys, tokens, account IDs, and where each one lives. URLs, hostnames, repo and release locations.
Then properly associate and store every durable observation, decision, opinion and thought that is not publicly available: anything that would be expensive or impossible to work out again from scratch.
Also store the session itself - as several one-claim memories, never one narrative: one for what was asked, one for what it turned into, one for what changed by the end, one for what is still open. That the work happened and what it did is information in its own right, sometimes more useful than any single detail inside it, and each of those claims is recalled on its own.
Skip: everything the STORE rule above excludes, anything already stored unless it is an update with additional or changed information, and the Compartment vault passphrase itself.
Show full SKILL.md (135 more words)Show less
Write each memory to stand alone: ONE claim of at most 200 characters by default - the vault enforces this and refuses lists, headings and paragraphs - with no pronouns pointing back at this conversation and no "as discussed above". Never leave out information that is necessary to understand the memory on its own. Several facts go through memory_store_many, one record each, in one call. Store preferences, stances and judgement calls with kind='opinion': opinions update instead of accumulate, and one resembling a live opinion comes back for an explicit supersedes=[old id] resend. Set namespace, tags and importance. When a fact was established before today, pass discovered=YYYY-MM-DD; the vault stamps every memory's dates itself, so never type dates into the text.
Do not stop early. Finish the sweep, then report how many were stored and how many updated.
© MaxFreedomPollard, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/compartmentalize of MaxFreedomPollard/Compartment.
Open the folder on GitHubat commit 43b5ccc
Compare with similar skills
Compartment Session Sweep next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Compartment Session Sweep this skillMaxFreedomPollard/Compartment | 578 | — | ~750 | Automated safety check: Pass | Apache-2.0 | |
| Memori Long-Term MemoryMemoriLabs/Memori | 17k | — | ~2k | Automated safety check: Notes | Custom licence | |
| Memori MCP Memory UsageMemoriLabs/Memori | 17k | — | ~3.8k | Automated safety check: Pass | MIT | |
| Ourmemourmem/omem | 174 | 1 repos | ~3.4k | Automated safety check: Pass | Custom licence | |
| Planning with FilesOthmanAdi/planning-with-files | 27k | — | ~2.9k | Automated safety check: Pass | MIT | |
| User Thoughts Memorysickn33/agentic-awesome-skills | 47k | 1 repos | ~2.5k | Automated safety check: Pass | MIT |
Similar skills
Memori MCP Memory Usage
MemoriLabs/Memori
Teaches an MCP-connected agent when and how to call Memori's recall, summary, compaction, augmentation, feedback and quota tools to keep context across sessions.
Ourmem
ourmem/omem
Shared memory that never forgets. An agent skill from ourmem/omem.
Planning with Files
OthmanAdi/planning-with-files
Keeps a task plan, findings and progress log in markdown files on disk so long agent tasks survive context resets, with Gemini hooks and helper scripts.
User Thoughts Memory
sickn33/agentic-awesome-skills
Saves a user's project decisions, rules and preferences into a project-local mdbase so later sessions and other agents can recover the intent.
Lemmalog
JordyZomer/lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP).
Related
Works with
Categories
Questions about Compartment Session Sweep
What does Compartment Session Sweep do?
Sweeps a conversation before compaction and saves durable facts, decisions and session records into the Compartment encrypted memory vault as short one-claim memories. The skill is meant to run before compacting or summarizing, or at any point to bank a session. It scans the whole conversation, including parts already summarized, and stores what is worth reusing: names and contacts, addresses, account IDs, lasting file locations and configuration, preferences, URLs and hostnames, durable decisions, and credentials together with where they live.
When should I use Compartment Session Sweep?
Compartment Session Sweep fits situations like: saving what matters from a long session before it is compacted; banking a finished piece of work into persistent memory; recording decisions, contacts and file locations for later sessions.
How do I install Compartment Session Sweep in Claude Code?
Run `npx skills add MaxFreedomPollard/Compartment --skill compartmentalize -a claude-code`. Or copy the skill folder (skills/compartmentalize in MaxFreedomPollard/Compartment) into .claude/skills/compartmentalize in your project. Claude Code loads it when a task matches its description.
How do I install Compartment Session Sweep in Codex?
Run `npx skills add MaxFreedomPollard/Compartment --skill compartmentalize -a codex`. Or copy the skill folder (skills/compartmentalize in MaxFreedomPollard/Compartment) into .agents/skills/compartmentalize in your project. Codex loads it when a task matches its description.
Can I use Compartment Session Sweep in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MaxFreedomPollard/Compartment --skill compartmentalize -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/compartmentalize, .gemini/skills/compartmentalize, .github/skills/compartmentalize and .opencode/skills/compartmentalize in your project.
What does Compartment Session Sweep need to run?
SKILL.md names no scripts, command-line tools or credentials: Compartment Session Sweep is instructions for the agent only. Our summary lists: Compartment, the encrypted memory vault, with its MCP memory tools.
Does Compartment Session Sweep access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Compartment Session Sweep safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Compartment Session Sweep use?
Compartment Session Sweep is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Compartment Session Sweep use?
About 750 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Compartment Session Sweep?
Skills that share tags, products or a category with Compartment Session Sweep: Memori Long-Term Memory (MemoriLabs/Memori, 17k stars), Memori MCP Memory Usage (MemoriLabs/Memori, 17k stars), Ourmem (ourmem/omem, 174 stars) and Planning with Files (OthmanAdi/planning-with-files, 27k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Compartment Session Sweep?
MaxFreedomPollard (a GitHub user) maintains it in MaxFreedomPollard/Compartment, which has 578 GitHub stars. The repository was last updated on September 30, 2026.
Source: MaxFreedomPollard/Compartment on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.