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 AtlasOmnia/donna-starter --skill hermes-session-maintenancegit clone --depth 1 https://github.com/AtlasOmnia/donna-starterWrote 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/atlasomnia/donna-starter/hermes-session-maintenance)<a href="https://agentmods.dev/skills/atlasomnia/donna-starter/hermes-session-maintenance"><img src="https://agentmods.dev/badge/skills/atlasomnia/donna-starter/hermes-session-maintenance/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/atlasomnia/donna-starter/hermes-session-maintenance"><img src="https://agentmods.dev/badge/skills/atlasomnia/donna-starter/hermes-session-maintenance.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 | $0.00037 | $0.02221 |
| Opus 5 | $0.00018 | $0.01111 |
| Sonnet 5 | $0.00007 | $0.00444 |
| Haiku 4.5 | $0.00004 | $0.00222 |
Grade A, and why
hermes-session-maintenance 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- hermes-session-maintenance — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Session Maintenance
Use this skill when the user asks about pruning Hermes sessions, session retention, session DB size, hermes sessions prune, sessions.auto_prune, sessions.retention_days, session export/backup, or whether old conversations should be capped.
Operating principles
- Treat this as Hermes configuration/maintenance work. If broader Hermes setup or CLI behavior is involved, also load
hermes-agentfor authoritative command references. - Do not assume retention policy from memory. Check live state before recommending destructive cleanup.
- Pruning is deletion. Prefer exporting a safety snapshot before the first aggressive prune or before reducing retention substantially.
- Distinguish default behavior from active behavior:
hermes sessions prunedefaults to--older-than 90.sessions.retention_daysmay also default to 90.sessions.auto_prune: falsemeans nothing is being deleted automatically.- Only ended sessions are prune candidates; active sessions are not pruned.
Standard workflow
- Inspect current volume:
hermes sessions stats
Use total sessions, messages, per-source counts, and DB size to shape the recommendation.
- Inspect prune command behavior when needed:
hermes sessions prune --help
- Check current config values:
hermes config show
If the summary output does not include the session settings, inspect the config file's sessions: block directly. Do not use hermes config get; this CLI supports show, edit, set, path, env-path, check, and migrate, not get.
- Recommend retention based on actual size and user needs.
- 90 days is conservative/default.
- 30 days is reasonable when the DB is multi-GB and session search is mostly used for recent operational continuity.
- Shorter than 30 days should usually be explicit user preference or a storage emergency.
- Before first major prune, export a backup:
hermes sessions export ~/hermes-sessions-backup-$(date +%Y%m%d).jsonl
What ships with it
3 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.
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 · 209 lines · 37 tokens per session scan A 4392af9d79b5
hermes-session-maintenance is a skill published in the GitHub repository AtlasOmnia/donna-starter (107 stars, last pushed 10d ago), licensed MIT. It adds 37 tokens to every session and 2,221 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
obsidian-memory-architecture
Use when designing, setting up, or maintaining an Obsidian vault as Hermes Agent's durable knowledge layer. Routes facts, conversation history, documents, procedures, and daily logs to the correct Hermes or vault system without duplicating everything into the prompt.
paleo-auto
Use when you want automatic token-saving without manual skill selection. Auto-detects long sessions (>15 turns), high token usage, or bulky context — then auto-enables paleo + paleo-trim-context + paleo-converse + paleo-budget at safe defaults. User does not need to think about which skill is active. Off: "disable…
paleo-trim-context
Use when context window is large / token cost high / long session. Proactively trim, summarize, or drop stale content to save context tokens without losing the task state.
paleo-converse
Use when user says "compress conversation", "condense chat", "summarize history", "too long context", or a session has many old turns. Condense prior conversation turns into a tight summary, merge near-duplicate messages, keep the last N turns verbatim. Saves context tokens without losing task state. Off: "stop…
hermes-context-optimization
Use this when the user asks about Hermes prompt/context size, “hello” startup cost, compression behavior, memory/profile bloat, tool-schema overhead, skill loading, session-store/search-index storage, or multimodal/visual-context approaches such as Snapcompact.
agent-dreaming-agnostic
Memory-agnostic background consolidation — reviews sessions, scores candidates, promotes durable insights to the active memory backend (built-in MEMORY.md or Holographic). Three-phase (Light/Deep/Condensation/REM). Run via cron or manually.