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 S3YED/appie-kit --skill hermes-dream-skillgit clone --depth 1 https://github.com/S3YED/appie-kitWrote 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/s3yed/appie-kit/hermes-dream-skill)<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.
<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>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 | $0.00056 | $0.00454 |
| Opus 5 | $0.00028 | $0.00227 |
| Sonnet 5 | $0.00011 | $0.00091 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
hermes-dream scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Hermes Dream Skill
Install on Hermes agents (Appie-3/4) for fleet-wide memory consolidation.
What It Does
03:10 AM — Hermes Agent
→ Read: memories/MEMORY.md, memories/USER.md, session transcripts (24h)
→ LLM consolidation (MiniMax M2.7 via api.minimaxi.chat)
→ Write: ~/hermes-dreams/YYYY-MM-DD.md
→ Deliver: push to fleet collection point OR message via Telegram
Setup (once per Hermes agent)
-
Create skill dir:
mkdir -p ~/.hermes/skills/hermes-dream -
Save this SKILL.md
-
Set up cron (via Hermes CLI or Telegram):
/cron add "hermes-dream consolidation" at 03:10 daily -
Ensure MINIMAX_API_KEY is in ~/.hermes/.env
Dream Output Format
# Hermes Dream: YYYY-MM-DD
## Nodes Memory
[machine-relevant memories]
## Session Patterns
[recurring themes from today]
## Cleanup Candidates
[old/stale entries]
## Fleet Notes
[things Appie-1 should know]
Collection
Appie-1 collects via:
# Via git push (Hermes pushes its dream to a git repo each morning)
# OR via:
ssh appie-1 "cat >> ~/memory/fleet-dreams/appie-4-$(date +%Y-%m-%d).md" < ~/hermes-dreams/YYYY-MM-DD.md
Key Notes for Hermes
- Use
hermes tools memory_addto persist key learnings - Use
hermes cronto manage the dream schedule - Dream skill auto-loads when "dream", "consolidate", or "sleep" mentioned
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.
- 9d ago First seen · 62 lines · 56 tokens per session scan A 06dee3d1dfdd
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.
Other skills, from other repositories
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
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.
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…
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…
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".
strategic-compact
Monitor context usage and suggest compaction at logical milestones.