Borrowing it
Nothing to install: this file belongs to danielsmithdevelopment/ClawQL. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/danielsmithdevelopment/ClawQL/main/.cursor/skills/clawql-vault-memory/SKILL.mdgit clone --depth 1 https://github.com/danielsmithdevelopment/ClawQLWrote 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/danielsmithdevelopment/clawql/clawql-vault-memory)<a href="https://agentmods.dev/skills/danielsmithdevelopment/clawql/clawql-vault-memory"><img src="https://agentmods.dev/badge/skills/danielsmithdevelopment/clawql/clawql-vault-memory/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/danielsmithdevelopment/clawql/clawql-vault-memory"><img src="https://agentmods.dev/badge/skills/danielsmithdevelopment/clawql/clawql-vault-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, 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 Prompt Injection · line 39 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 42 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 43 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 47 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00088 | $0.02350 |
| Opus 5.5 | $0.00035 | $0.00940 |
| Sonnet 5.5 | $0.00018 | $0.00470 |
| Haiku 4.5 | $0.00009 | $0.00235 |
Grade A, and why
clawql-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 1mo 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClawQL vault memory (deep ingest + recall)
When to apply
- Ingest: After meaningful outcomes—decisions, debugging conclusions, API/env contracts, runbooks, user preferences, cross-feature relationships.
- Recall: Before deep work, when the user references past work, or when vault context could reduce wrong assumptions.
If ClawQL MCP is not configured or CLAWQL_OBSIDIAN_VAULT_PATH is unset, say so briefly and continue without blocking.
Cursor Agent: call_mcp_tool server parameter
Your mcp.json key can stay clawql (that is what Settings / docs refer to). The agent call_mcp_tool API does not accept that bare string: Cursor registers the server under a scoped id derived from where the config lives:
| Config file | Typical call_mcp_tool server value |
|---|---|
~/.cursor/mcp.json |
user-clawql |
${workspaceFolder}/.cursor/mcp.json |
workspace-clawql |
There is no supported mcp.json field to rename this to bare clawql for call_mcp_tool—the prefix is host behavior to avoid collisions (e.g. the same key in user vs project config). If both files define clawql, two scoped servers can exist; use the one that matches where you configured ClawQL for this workspace.
Never store secrets: tokens, API keys, passwords, private keys, or raw session cookies. Summarize redacted config instead.
Tool capabilities (what the server actually does)
memory_ingest
| Field | Use |
|---|---|
title |
Required. Drives the H1 and the filename slug under Memory/<slug>.md. Prefer stable, descriptive titles (e.g. gRPC MCP ListTools metadata) so updates append to the same page. |
insights |
Primary prose. Markdown is fine. This is where semantic tagging and structure live (see below). |
conversation |
Longer transcript or chat summary; stored in a fenced block under Conversation. |
toolOutputs |
Verbatim logs: command output, errors, JSON snippets, diffs—each string becomes a block; multiple strings are separated for readability. |
toolOutputsFile |
Server-side only: a path (absolute or relative to the ClawQL process cwd) the MCP server reads as UTF-8 and uses as toolOutputs. Use for large bodies so the model only passes a short path in the tool call (not the file contents). Must fall under an allowlist (CLAWQL_MEMORY_INGEST_FILE_ROOTS, or default realpath of cwd). If both toolOutputsFile and toolOutputs are set, the file wins. Disable reads with CLAWQL_MEMORY_INGEST_FILE=0. |
wikilinks |
List of other vault note titles (plain names; [[brackets]] optional). Rendered as ## Related with - [[Note Name]] bullets—this is the graph for Obsidian. |
sessionId |
Optional label for the section header (threads multi-step work). |
append |
Default true: new section appended to an existing file with the same slug. Set false only to replace the file body (rare). |
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.
- 1mo ago First seen · 157 lines · 88 tokens per session scan A a22913be6bd2
clawql-vault-memory is a skill published in the GitHub repository danielsmithdevelopment/ClawQL (13 stars, last pushed today), licensed Apache-2.0. It adds 88 tokens to every session and 2,350 once invoked, about $0.0004 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 2026-08-30.
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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.