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 MelloB1989/KARMAX --skill fleet-memorygit clone --depth 1 https://github.com/MelloB1989/KARMAXWrote 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/mellob1989/karmax/fleet-memory)<a href="https://agentmods.dev/skills/mellob1989/karmax/fleet-memory"><img src="https://agentmods.dev/badge/skills/mellob1989/karmax/fleet-memory/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/mellob1989/karmax/fleet-memory"><img src="https://agentmods.dev/badge/skills/mellob1989/karmax/fleet-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00578 |
| Opus 5.5 | $0.00000 | $0.00231 |
| Sonnet 5.5 | $0.00000 | $0.00116 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
fleet-memory 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The operator's memory
The operator keeps a long-term memory: people, projects, decisions, preferences, what was tried and why. The orchestrator saves to it. You can read it and suggest additions; you never write it.
When to recall
Before you start work on a person, a project or a decision the operator has history with, search for it:
fleetctl memory recall "ram build host" # the 5 best matches
fleetctl memory recall "slate release plan" --limit 10 --json
Search in plain words, a few at a time ("who reviews slate PRs", "billing migration decision"). Treat what comes back as context the operator gave you, and say in your report when it changed what you did. It can be out of date: when it disagrees with the code or with your brief, the brief wins; mention the disagreement.
How to suggest
When you learn something durable that the operator would want kept (a preference, a decision and its reason, who owns what), suggest it:
fleetctl memory suggest "Ram prefers squash merges on slate-server" --why "he asked for it in review of PR 31"
One fact per suggestion, a sentence or two that stands alone without this conversation. The suggestion goes to the orchestrator, which decides whether to save it; you hear nothing back. Do not suggest task progress, guesses, or anything already in the code or the docs.
Never put secrets in a suggestion: no tokens, keys, passwords, connection strings or personal data the operator did not ask to keep. The memory is read by every session the operator runs.
Who may
The operator, their Claude sessions and the orchestrator always may. An agent may only while its current task was given by the operator, one of their sessions or the orchestrator; on a task a colleague gave, both commands answer 403. Colleagues on the tailnet never may. fleetd decides this from its ledger; there is nothing to configure.
From any Claude Code session
The same two tools are an MCP server wherever fleetctl works (a fleet host, a laptop on the tailnet, an agent):
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.
- 4d ago First seen · 55 lines · 0 tokens per session scan A 65afe80973f0
fleet-memory is a skill published in the GitHub repository MelloB1989/KARMAX (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 578 tokens. 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 2026-10-25.
Other skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…