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 MaxFreedomPollard/Compartment --skill compartmentalizegit clone --depth 1 https://github.com/MaxFreedomPollard/CompartmentWrote 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/maxfreedompollard/compartment/compartmentalize)<a href="https://agentmods.dev/skills/maxfreedompollard/compartment/compartmentalize"><img src="https://agentmods.dev/badge/skills/maxfreedompollard/compartment/compartmentalize/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/maxfreedompollard/compartment/compartmentalize"><img src="https://agentmods.dev/badge/skills/maxfreedompollard/compartment/compartmentalize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.00645 |
| Opus 5.5 | $0.00022 | $0.00258 |
| Sonnet 5.5 | $0.00011 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
compartmentalize 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 28d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- compartmentalize — 92% identical, 10 lines differ
What it actually says
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.
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.
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.
- 28d ago Changed · +6 lines · +2 tokens per session 459c9d244c85
- 1mo ago First seen · 53 lines · 52 tokens per session scan A 0ddb1ec0911c
compartmentalize is a skill published in the GitHub repository MaxFreedomPollard/Compartment (577 stars, last pushed 8d ago), licensed Apache-2.0. It adds 54 tokens to every session and 645 once invoked, about $0.0002 per session on Opus 5.5. 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
openclaw-skill
Gives your OpenClaw agent persistent, encrypted memory that survives across sessions. Store thoughts, decisions, skills learned, and preferences. Recall them next session. Share knowledge with other agents via the Commons.
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
memanto-companion
Inspect and manage the cross-session engineering memory that Memanto maintains for your Claude Code skills. Use when the user asks what Memanto remembers, wants to see their engineering profile, manually recall context for a skill, or store a decision. The automatic lifecycle hooks handle capture/injection on their…
openlore
Query and publish to an OpenLore knowledge repository over SSH using ordinary shell commands. Use when a task needs project documentation, runbooks, shared team knowledge, or a place to publish findings.
Context Doctor
Investigate and repair an agent's context — memory, system prompt, and skills — using observed behavior as evidence. Use when the user asks to audit, clean up, or fix your memory or context, or runs /doctor. Do not load for routine memory reads or edits, or requests that merely mention memory.