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-mnemosynegit 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-mnemosyne)<a href="https://agentmods.dev/skills/atlasomnia/donna-starter/hermes-mnemosyne"><img src="https://agentmods.dev/badge/skills/atlasomnia/donna-starter/hermes-mnemosyne/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-mnemosyne"><img src="https://agentmods.dev/badge/skills/atlasomnia/donna-starter/hermes-mnemosyne.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 53 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00030 | $0.03528 |
| Opus 5 | $0.00015 | $0.01764 |
| Sonnet 5 | $0.00006 | $0.00706 |
| Haiku 4.5 | $0.00003 | $0.00353 |
Grade A, and why
hermes-mnemosyne 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 12d 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-mnemosyne — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Mnemosyne Memory Provider
Mnemosyne is Hermes' primary local-first memory engine — SQLite with vector + FTS5 hybrid search, 19+ tools, auto-consolidation, and a standalone CLI. It's a pip-installed plugin (not a built-in toolset) discovered via $HERMES_HOME/plugins/mnemosyne/.
Quick Reference
When comparing memory stacks for the user, use references/memory-tool-selection-mem0-vs-mnemosyne.md: Mnemosyne is preferred for Hermes local-first profile memory; Mem0 is the safer productized choice for external/customer-facing apps.
For migrations from overlapping stacks such as LCM + built-in memory + gBrain, use references/memory-stack-migration-pilot.md. Prefer a staged simplification: preserve LCM, pilot Mnemosyne as the external memory provider, keep the incumbent system read-only for rollback, and retire redundant writers after measured acceptance.
| What | How |
|---|---|
| Check if active | hermes memory status or check memory.provider in config.yaml |
| Memory stats | mnemosyne stats (CLI) or mnemosyne_stats (tool) |
| Manual consolidation | mnemosyne sleep (current session) or mnemosyne sleep --all-sessions |
| Dry-run consolidation | mnemosyne sleep --all-sessions --dry-run |
| Enable auto-consolidation | Set memory.auto_sleep: true + memory.sleep_threshold: 50 in config.yaml |
| Use Hermes' model for compression | MNEMOSYNE_HOST_LLM_ENABLED=true in .env |
| Check if installed | hermes memory status; if the symlink is missing, run ~/.hermes/hermes-agent/venv/bin/mnemosyne-install |
Architecture
Mnemosyne is a memory provider, not a toolset. Its tools (mnemosyne_remember, mnemosyne_recall, mnemosyne_sleep, etc.) are injected through the memory manager — they are NOT accessible via enabled_toolsets. Do NOT use enabled_toolsets: ["mnemosyne"] in cron jobs or delegation configs.
Installation path and package split
Treat Mnemosyne as two moving parts:
mnemosyne-memory— core memory engine and optional embedding/local-LLM extras.mnemosyne-hermes— Hermes adapter/plugin package used by current upstream installation guidance.
What ships with it
4 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.
- 12d ago First seen · 244 lines · 30 tokens per session scan A 9650e20e9560
hermes-mnemosyne is a skill published in the GitHub repository AtlasOmnia/donna-starter (111 stars, last pushed 13d ago), licensed MIT. It adds 30 tokens to every session and 3,528 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
google-cloud-storage-fuse
Mounts Cloud Storage buckets as a POSIX file system with Cloud Storage FUSE (gcsfuse). Use when interacting with gcsfuse: decide whether FUSE, native gs:// reads, or Filestore/Managed Lustre fits a workload, deploy tuned mounts on GKE, Compute Engine, or Cloud Run, enable and size file, stat, and list caches, tune…
tanstack-ai-memory-redis
Use when wiring redis() from @tanstack/ai-memory/redis in production — covers client setup (ioredis or node-redis via fromNodeRedis), the storage model, client-side ranking limits, and troubleshooting.
hunt-nosqli
Hunt NoSQL Injection — MongoDB operator injection ($where, $regex, $gt, $ne), CouchDB, Redis command injection, auth bypass via NoSQLi, data dump. Use when target uses MongoDB/Mongoose, CouchDB, Redis, or shows NoSQL error messages.
aws-cloudformation-elasticache
Provides AWS CloudFormation patterns for ElastiCache Redis or Memcached infrastructure, including subnet groups, parameter groups, security controls, and cross-stack outputs. Use when designing cache tiers, high-availability replication groups, encryption settings, or reusable CloudFormation templates for application…
spring-boot-cache
Provides patterns for implementing Spring Boot caching: configures Redis/Caffeine/EhCache providers with TTL and eviction policies, applies @Cacheable/@CacheEvict/@CachePut annotations, validates cache hit/miss behavior, and exposes metrics via Actuator. Use when adding caching to Spring Boot services, configuring…
caching-strategies
CDN, Redis, in-memory cache, cache invalidation, and distributed caching patterns.