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 zycaskevin/Vault-Agent-Memory --skill openclawgit clone --depth 1 https://github.com/zycaskevin/Vault-Agent-MemoryWrote 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/zycaskevin/vault-agent-memory/openclaw)<a href="https://agentmods.dev/skills/zycaskevin/vault-agent-memory/openclaw"><img src="https://agentmods.dev/badge/skills/zycaskevin/vault-agent-memory/openclaw.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.00531 |
| Opus 5 | $0.00023 | $0.00266 |
| Sonnet 5 | $0.00009 | $0.00106 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
vault-for-llm 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.
What it actually says
Vault Agent Memory for OpenClaw
Use this skill when OpenClaw needs durable project knowledge from Vault Agent Memory.
Vault is not an always-on chat memory dump. Treat it as governed project memory: confirmed decisions, source-of-truth notes, pitfalls, SOPs, repo docs, and reviewed handoff knowledge.
Agent Rules
- Search before answering project-memory questions.
- Do not treat search preview text as final evidence.
- If a result has
id,node_uid, orline_start/line_end, use bounded read before citing it. - Cite the source title and line range returned by Vault when making claims.
- Use candidate-first memory:
- For new observations, use
vault_memory_propose. - Do not promote candidates unless a human operator explicitly asks.
- Do not use direct
vault_addfor autonomous memories.
- For new observations, use
- Keep secrets out of memory. If content may include tokens, API keys, private credentials, or customer data, ask before storing.
Commands
vault-openclaw init
vault-openclaw search "deployment checklist" --limit 5
vault-openclaw read-range 12 --line-start 20 --line-end 55
vault-openclaw mcp-config
Database Scope
OpenClaw shares memory with other agents only when they use the same Vault
project directory. If OpenClaw should join a shared project memory, configure the
plugin projectDir to the same path used by Hermes, Codex, Claude Code, or n8n.
Use a separate projectDir for isolated experiments.
Recommended Loop
vault_search -> vault_read_range -> answer with source
For new memory:
vault_memory_propose -> human review -> vault_memory_promote only after approval
What ships with it
7 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 · 73 lines · 46 tokens per session scan A 62bd25d1fd77
vault-for-llm is a skill published in the GitHub repository zycaskevin/Vault-Agent-Memory (49 stars, last pushed 10d ago), licensed Apache-2.0. It adds 46 tokens to every session and 531 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
rekal-init
Bootstrap rekal memory for a project. Scans the codebase for architecture, conventions, dependencies, workflows, and config, then stores durable knowledge as properly typed, tagged, deduplicated memories. Use when starting rekal on a new project, or when user says "init rekal", "bootstrap memory", "populate rekal"…
rekal-save
End-of-session memory capture with deduplication. Extracts durable knowledge, checks for duplicates, stores or replaces as appropriate. Use whenever a session wraps up, a task finishes, or the user says goodbye/thanks/done. Also use when significant preferences, decisions, or discoveries emerge mid-session. Make sure…
rekal-usage
Operational guide for rekal memory tools. Precise rules for when/how to call each tool, with exact parameters and decision trees. Use at session start, when onboarding to a rekal workspace, or when user asks "how do I use rekal", "what rekal tools", "help with memory". Trigger: /rekal-usage.
rekal-hygiene
Periodic memory maintenance and cleanup. Finds duplicates, contradictions, and quality issues in the memory database. Proposes fixes for user approval. Never auto-deletes or auto-modifies. Use when user says "clean up memories", "memory maintenance", "check memory health", or invokes /rekal-hygiene. Run monthly or…
any-mcp
Use when an agent needs to read, search, create, edit, organize, upload, or chat with Anytype through the bounded any-mcp server. Covers safe tool selection, exact identifier chaining, optional toolsets, common PKM workflows, and the narrow anyr fallbacks for chat subscriptions and rich chat blocks.
alice-memory
Use Alice as the user's durable local memory. Load before answering from context, and whenever you learn something worth keeping across sessions.