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 turmyshevd/openclawgotchi --skill vault-memorygit clone --depth 1 https://github.com/turmyshevd/openclawgotchiWrote 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/turmyshevd/openclawgotchi/vault-memory)<a href="https://agentmods.dev/skills/turmyshevd/openclawgotchi/vault-memory"><img src="https://agentmods.dev/badge/skills/turmyshevd/openclawgotchi/vault-memory.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 | $0.00030 | $0.00844 |
| Opus 5 | $0.00015 | $0.00422 |
| Sonnet 5 | $0.00006 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
vault-memory 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vault Memory
Use this skill when the task is about remembering, recalling, organizing, deduplicating, or validating project knowledge stored in .workspace/knowledge/.
This skill is about memory quality, not visual note polish.
Goals
- Make recall reliable.
- Keep metadata internally consistent.
- Preserve stable links and note identities.
- Avoid creating duplicate notes when extending existing knowledge is better.
Mental Model
Treat the vault as four layers:
inbox/- raw intake lognotes/- atomic working knowledgeprojects/andtopics/- hub/index layer- frontmatter + links + tags - retrieval surface
If recall is poor, first inspect layer 4 before rewriting layer 2.
Required Invariants
Every operational note should have:
idtypenote_typecreatedsourceprojecttopicstatustags
And these must stay consistent:
statusmust match astatus/*tag if such tags are usedprojectshould match the linked project hub when obvioustopicshould match the linked topic hub when obvious- filenames, titles, and links should remain stable unless there is a strong reason to rename
Retrieval-First Rules
When writing or updating notes, optimize for future retrieval:
- Prefer explicit titles over clever titles.
- Put canonical terms in the title or first paragraph.
- Keep the first 2-4 lines dense with searchable meaning.
- Preserve important domain terms from the source text.
- If the note is about a named system, product, or workflow, mention that exact name early.
- If the same concept appears in multiple languages, keep the original wording somewhere in the note.
Duplicate Policy
Before creating a new note:
- Search the vault for the core entity and concept.
- If an existing note already owns the topic, extend it instead of creating a sibling.
- Only create a new note when the new material has a distinct purpose:
- different artifact type
- different project
- different time-bounded report
- different decision or workflow
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 · 127 lines · 30 tokens per session scan A ad9ec16f3a9a
vault-memory is a skill published in the GitHub repository turmyshevd/openclawgotchi (48 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 844 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
add-compact
Add /compact command for manual context compaction. Solves context rot in long sessions by forwarding the SDK's built-in /compact slash command. Main-group or trusted sender only.
add-qmd
Add QMD (Query Markup Documents) as an advanced memory search backend. Upgrades the built-in grep-based memorysearch with hybrid BM25 + vector semantic search + LLM re-ranking. Fully local, no API keys needed. Triggers on "add qmd", "qmd memory", "semantic memory search", "upgrade memory".
swmm-modeling-memory
Read historical Agentic SWMM experiment audit artifacts and summarize repeated assumptions, QA issues, failures, missing evidence, run-to-run differences, lessons learned, and controlled skill update proposals. Use downstream of swmm-experiment-audit when multiple audited runs exist or when a user asks for modeling…
zhigui
Personal assistant workflow for durable memory, connected actions, decisions, planning and review. Use whenever the user discusses their life, commitments, goals, notes, choices, follow-ups, or schedule.
agent-browser
A command-line tool for controlling a web browser without a visible window. It can open pages, inspect their accessibility structure, interact with forms, take screenshots, create PDFs, and run JavaScript.
web-research
A command-line web research tool that searches the internet and turns web pages into clean Markdown text. SearXNG provides privacy-focused search, while Jina Reader fetches page content without opening a browser.