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/hermes-custom-pack --skill obsidian-memory-architecturegit clone --depth 1 https://github.com/AtlasOmnia/hermes-custom-packWrote 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/hermes-custom-pack/obsidian-memory-architecture)<a href="https://agentmods.dev/skills/atlasomnia/hermes-custom-pack/obsidian-memory-architecture"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/obsidian-memory-architecture/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/hermes-custom-pack/obsidian-memory-architecture"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/obsidian-memory-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Privilege Escalation · line 51 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.03111 |
| Opus 5 | $0.00028 | $0.01555 |
| Sonnet 5 | $0.00011 | $0.00622 |
| Haiku 4.5 | $0.00006 | $0.00311 |
Grade A, and why
obsidian-memory-architecture 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obsidian Memory Architecture for Hermes Agent
Overview
Use Obsidian as Hermes Agent's human-readable, durable knowledge layer—not as a replacement for every native memory system. Modern Hermes already has bounded built-in memory, searchable session history, optional external memory providers, reusable skills, and scheduled jobs. The vault complements those systems by holding documents, decisions, project state, daily notes, and material that should remain useful even when Hermes is offline.
The central rule is simple:
Store information according to how it must be retrieved and maintained, not according to where there happens to be room.
This skill extends the bundled obsidian skill. The bundled skill covers filesystem operations; this one defines architecture, routing, ownership, maintenance, and automation.
When to Use
Use when:
- setting up an Obsidian vault for Hermes;
- deciding whether information belongs in memory, session history, a skill, or the vault;
- creating daily-note, project, decision, or troubleshooting workflows;
- coordinating multiple Hermes profiles through one vault;
- migrating an older
MEMORY.md-heavy setup to current Hermes capabilities; - reducing prompt bloat without losing durable knowledge.
Do not use for:
- ordinary note editing only—load the bundled
obsidianskill; - storing a single durable preference—use the active memory provider;
- recalling a past conversation—use
session_searchfirst; - documenting a repeatable command sequence—create or update a skill;
- storing secrets, access tokens, or credentials—the vault is not a secret manager.
Current Hermes Storage Model
Treat these as separate layers with different jobs:
| Layer | Best use | Retrieval | Avoid |
|---|---|---|---|
Built-in USER.md / MEMORY.md |
Tiny universal identity, preferences, and environment facts | Injected at session start | Project diaries, long procedures, raw logs |
| Optional memory provider | Durable facts, entities, preferences, and semantic recall | Automatically or through provider tools | Canonical documents and large artifacts |
session_search |
Exact prior conversation history and task outcomes | On-demand FTS search | Facts that must always be available |
| Obsidian vault | Canonical documents, decisions, project state, daily timeline, research | Filesystem search/read | Secrets and duplicated chat transcripts |
| Hermes skills | Reusable procedures, commands, pitfalls, verification | Loaded when relevant | One-time outcomes and personal diary entries |
| Cron output/cache | Scheduled collection and transient machine state | Job history or cache files | Permanent knowledge unless deliberately promoted |
What ships with it
9 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.
- README.md 4.9 KB
- scripts/scaffold_vault.py 6.5 KB runs code
- scripts/validate_skill.py 1.9 KB runs code
- templates/Assistant-Knowledge-Map.md 867 B
- templates/Daily.md 138 B
- templates/Decision.md 182 B
- templates/Project.md 217 B
- tests/test_scaffold.py 3.2 KB runs code
- tests/test_validate_skill.py 1.1 KB runs code
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.
- 10d ago First seen · 353 lines · 56 tokens per session scan A d40023be805f
obsidian-memory-architecture is a skill published in the GitHub repository AtlasOmnia/hermes-custom-pack (56 stars, last pushed 26d ago), licensed MIT. It adds 56 tokens to every session and 3,111 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 2026-08-30.
Other skills, from other repositories
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.
agent-dreaming
DEPRECATED — use agent-dreaming-agnostic instead. Background memory consolidation for built-in MEMORY.md only.
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.
hermes-mnemosyne
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 $HERMESHOME/plugins/mnemosyne/.
hermes-session-maintenance
Use this skill when the user asks about pruning Hermes sessions, session retention, session DB size, hermes sessions prune, sessions.autoprune, sessions.retentiondays, session export/backup, or whether old conversations should be capped.
mnemosyne-maintenance
Use when: upgrading Mnemosyne, diagnosing slow/hung consolidation (mnemosynesleep), fixing missing embeddings, or troubleshooting import/version mismatches.