hermes-dream

hermes-dream is a skill for Claude Code, Codex from S3YED/appie-kit. It costs 56 tokens per session (454 once invoked), scanned A, original, MIT.

A nightly memory-consolidation routine for Hermes agents named Appie-3 and Appie-4. It reads recent memories and session transcripts, creates a dated summary, and sends it to the fleet.

In plain words
What is it for?
It is for scheduled overnight memory cleanup and sharing, using a 03:10 AM cron job, a MiniMax model, local dream files, and either Git or Telegram delivery.
Why use it?
It turns scattered daily memories into a record of useful facts, recurring patterns, stale information, and notes for other agents.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for scheduled overnight memory cleanup and sharing, using a 03:10 AM cron job, a MiniMax model, local dream files, and either Git or Telegram delivery.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/s3yed/appie-kit/hermes-dream-skill
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.

Any agent
npx skills add S3YED/appie-kit --skill hermes-dream-skill
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 hermes-dream

README.md
[![agentmods](https://agentmods.dev/badge/skills/s3yed/appie-kit/hermes-dream-skill/github.svg)](https://agentmods.dev/skills/s3yed/appie-kit/hermes-dream-skill)
Your own site
<a href="https://agentmods.dev/skills/s3yed/appie-kit/hermes-dream-skill"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/hermes-dream-skill/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.

agentmods 80×15 button for hermes-dream

Your own site · 80×15
<a href="https://agentmods.dev/skills/s3yed/appie-kit/hermes-dream-skill"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/hermes-dream-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 454 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00056 $0.00454
Opus 5 $0.00028 $0.00227
Sonnet 5 $0.00011 $0.00091
Haiku 4.5 $0.00006 $0.00045

Measured 9d ago against content hash 06dee3d1dfdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

hermes-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 9d 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.

skills/automation/hermes-dream-skill/SKILL.md · 62 lines

What it actually says

Hermes Dream Skill

Install on Hermes agents (Appie-3/4) for fleet-wide memory consolidation.

What It Does

03:10 AM — Hermes Agent
  → Read: memories/MEMORY.md, memories/USER.md, session transcripts (24h)
  → LLM consolidation (MiniMax M2.7 via api.minimaxi.chat)
  → Write: ~/hermes-dreams/YYYY-MM-DD.md
  → Deliver: push to fleet collection point OR message via Telegram

Setup (once per Hermes agent)

  1. Create skill dir: mkdir -p ~/.hermes/skills/hermes-dream

  2. Save this SKILL.md

  3. Set up cron (via Hermes CLI or Telegram): /cron add "hermes-dream consolidation" at 03:10 daily

  4. Ensure MINIMAX_API_KEY is in ~/.hermes/.env

Dream Output Format

# Hermes Dream: YYYY-MM-DD
## Nodes Memory
[machine-relevant memories]
## Session Patterns
[recurring themes from today]
## Cleanup Candidates
[old/stale entries]
## Fleet Notes
[things Appie-1 should know]

Collection

Appie-1 collects via:

# Via git push (Hermes pushes its dream to a git repo each morning)
# OR via:
ssh appie-1 "cat >> ~/memory/fleet-dreams/appie-4-$(date +%Y-%m-%d).md" < ~/hermes-dreams/YYYY-MM-DD.md

Key Notes for Hermes

  • Use hermes tools memory_add to persist key learnings
  • Use hermes cron to manage the dream schedule
  • Dream skill auto-loads when "dream", "consolidate", or "sleep" mentioned
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. 9d ago First seen · 62 lines · 56 tokens per session scan A 06dee3d1dfdd

Subscribe to this mod's changes

hermes-dream is a skill published in the GitHub repository S3YED/appie-kit (8 stars, last pushed 13d ago), licensed MIT. It adds 56 tokens to every session and 454 once invoked, about $0.0003 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

strategic-compact

Monitor context usage and suggest compaction at logical milestones.

mshadmanrahman/pm-pilot · 15 tokens