fleet-dream

fleet-dream is a skill for Claude Code, Codex from S3YED/appie-kit. It costs 80 tokens per session (368 once invoked), scanned A, original, MIT.

A nightly process that combines memory from several AI agents into shared fleet-level notes. Memory consolidation means collecting separate records and summarizing useful recurring insights.

In plain words
What is it for?
Use it to run or inspect the nightly 03:05 consolidation, collect agent memory files, and write unified dream logs and updated daily memory.
Why use it?
It prevents useful observations from remaining isolated on individual machines and keeps a shared record of what the agent fleet has learned.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Install

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.

agentmods
npx agentmods add skills/s3yed/appie-kit/fleet-dream
Any agent
npx skills add S3YED/appie-kit --skill fleet-dream
Clone the repo
git clone --depth 1 https://github.com/S3YED/appie-kit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for fleet-dream

README.md
[![agentmods](https://agentmods.dev/badge/skills/s3yed/appie-kit/fleet-dream.svg)](https://agentmods.dev/skills/s3yed/appie-kit/fleet-dream)
Your own site
<a href="https://agentmods.dev/skills/s3yed/appie-kit/fleet-dream"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/fleet-dream.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 368 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00080 $0.00368
Opus 5 $0.00040 $0.00184
Sonnet 5 $0.00016 $0.00074
Haiku 4.5 $0.00008 $0.00037

Measured 6d ago against content hash a96beda27467, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fleet-dream 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 6d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/fleet-dream.sh, scripts/install-ssh-keys.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/automation/fleet-dream/SKILL.md · 41 lines

What it actually says

Fleet Dream — Cross-Fleet Memory Consolidation

Runs every night at 03:05 AM. Collects memory from all agents, consolidates with MiniMax M2.7, writes to memory/fleet-dreams/.

How It Works

03:05 AM — Appie-1 (Mac Mini)
  ├─ SSH → Appie-2: collect ~/.openclaw/memory/YYYY-MM-DD.md
  ├─ SSH → Appie-3: collect ~/.hermes/memories/*.md
  ├─ SSH → Appie-4: collect ~/.hermes/memories/*.md
  └─ Local:  ~/memory/YYYY-MM-DD.md
         ↓
  MiniMax M2.7 consolidation prompt
         ↓
  Writes:
  - ~/memory/fleet-dreams/YYYY-MM-DD.md (unified fleet dream log)
  - Updates ~/memory/YYYY-MM-DD.md with fleet-level insights

Manual Trigger

/fleet-dream

Or from this skill: "Run the fleet dream now"

Config

  • scripts/fleet-dream.sh — main cron script
  • memory/fleet-dreams/ — consolidated dream logs
  • Schedule: 5 3 * * * (3:05 AM daily)
Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 6d ago First seen · 41 lines · 80 tokens per session scan A a96beda27467

Subscribe to this mod's changes

fleet-dream is a skill published in the GitHub repository S3YED/appie-kit (7 stars, last pushed 10d ago), licensed MIT. It adds 80 tokens to every session and 368 once invoked, about $0.0004 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

hive.context-preservation

Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.

aden-hive/hive · 24 tokens

hive.note-taking

Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.

aden-hive/hive · 30 tokens

caveman-compress

Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or…

stevesolun/ctx · 77 tokens

dream

Prunes and consolidates the project's auto-memory to keep it minimal — deletes stale, wrong, or redundant memories, merges overlapping ones into existing files, and trims the index. Strong bias against growth: never creates new memory files and never stores new facts. Verifies staleness against the current codebase…

oprogramadorreal/optimus-claude · 85 tokens

people-sync

Pulls a Granola meeting transcript and updates people files with per-person intelligence: what they said, what they pushed back on, what they committed to. Compounds over time — each meeting adds a layer. Triggers on: "sync people", "update people from meeting", "update stakeholders", "/people-sync".

mshadmanrahman/pm-pilot · 67 tokens

handoff-doc

Create portable handoff document when switching sessions.

mshadmanrahman/pm-pilot · 12 tokens