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 glebis/claude-skills --skill open-knowledge-vaultgit clone --depth 1 https://github.com/glebis/claude-skillsWrote 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/glebis/claude-skills/open-knowledge-vault)<a href="https://agentmods.dev/skills/glebis/claude-skills/open-knowledge-vault"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/open-knowledge-vault/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/glebis/claude-skills/open-knowledge-vault"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/open-knowledge-vault.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 | $0.00058 | $0.00929 |
| Opus 5.5 | $0.00023 | $0.00372 |
| Sonnet 5.5 | $0.00012 | $0.00186 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
open-knowledge-vault 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 7d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Knowledge Vault
Keep the knowledge readable without Obsidian. Use OKF v0.2 as the core, and make Dataview an optional view. Preserve existing human content and metadata when maintaining a vault.
Choose the scope
Inspect the requested vault, its instructions, schema, links, plugins, and current sources before writing. Infer the goal from the request; ask only for missing choices that affect the outcome. For a new bundle default to portable Markdown, with Obsidian setup or Dataview only when requested. Do not assume the user's personal vault is the destination.
Profiles are optional producer conventions, not OKF requirements:
- meeting: sources, concepts, ideas, events, questions, actions, people, organisations, maps
- learning: domains, courses, lessons, concepts, scenarios, questions, review tasks
- research/project: references, claims, decisions, procedures, questions, actions
Adapt the taxonomy to the material. Do not create empty notes to hit a count. A framework can organise a talk, but mark planned sections separately from delivered content.
Setup and audit
Use scripts/vault.py init PATH --title TITLE --profile meeting|learning|research for a new bundle. It only creates missing files. Add --obsidian for local Markdown-link preferences and --dataview for a dashboard with ordinary links plus optional queries. Templates are outside the bundle in this skill, not untyped Markdown inside it.
Use scripts/vault.py audit PATH to check basic OKF structure. Errors affect core conformance; warnings flag advisory metadata and portable-link issues. This is a structural check, not verification of the knowledge or a certification of all OKF features. Read references/format.md when writing metadata or adapting an existing vault.
Dataview installation is a separate optional command: scripts/vault.py dataview PATH --from-plugin DIR. Use a user-installed build or the official release chosen by the user. Copy only manifest, main, and styles; preserve other plugins and existing settings. New settings disable DataviewJS. It does not fetch software or copy personal plugin state. Reload the vault and verify a rendered query before claiming activation. A configured plugin list alone is not proof that it loaded.
What ships with it
5 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.
- 7d ago First seen · 46 lines · 58 tokens per session scan A 4b7f019682ff
open-knowledge-vault is a skill published in the GitHub repository glebis/claude-skills (392 stars, last pushed 8d ago), licensed MIT. It adds 58 tokens to every session and 929 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-09.
Other skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.