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 knowz-io/deepseek-knowz-plugin --skill knowz-autogit clone --depth 1 https://github.com/knowz-io/deepseek-knowz-pluginWrote 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/knowz-io/deepseek-knowz-plugin/knowz-auto)<a href="https://agentmods.dev/skills/knowz-io/deepseek-knowz-plugin/knowz-auto"><img src="https://agentmods.dev/badge/skills/knowz-io/deepseek-knowz-plugin/knowz-auto.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 | $0.00044 | $0.00746 |
| Opus 5 | $0.00022 | $0.00373 |
| Sonnet 5 | $0.00009 | $0.00149 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
knowz-auto 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowz Auto — Lightweight routing
Treat this as a lightweight helper skill. The agent may surface it when a message looks like Knowz query, save, or amend intent, but do not assume guaranteed background auto-execution.
Instructions
- Read
knowz-vaults.mdif it exists. - Ignore clear build-only requests such as "fix this bug", "add a test", or "implement this feature".
- Classify the message:
- Query intent: "why did we", "what is our convention", "did we already", "have we done this before"
- Save intent: "we decided", "I learned", "the workaround is", "save this", "capture this"
- Amend intent: "update the X entry to...", "fix the typo in the X note", "append Y to the X entry", "change the tag on X", "amend this in the vault", "edit the X in knowz"; the user references an item that already exists and describes a delta, not a brand-new insight.
- If query intent matches a configured vault rule:
- run a lightweight direct
mcp__knowz__search_knowledgeormcp__knowz__ask_questioncall from the current agent - weave successful findings into the response naturally
- run a lightweight direct
- If save intent matches a configured vault rule:
- ask the user whether to save it
- if they agree, hand off to the same workflow as
/knowz-save
- If amend intent matches a configured vault rule:
- call
mcp__knowz__search_knowledgescoped to the matched vault (limit: 5) to locate the target item - if exactly one clear match → proceed. If multiple plausible matches → present the top 3 with titles/snippets and ask the user which one. If zero matches → say so and offer
/knowz-saveinstead. - confirm the change with the user: show the target item title and the proposed delta; never auto-amend
- before the mutation, derive a stable
Idempotency Keyfromamend, the resolved vault,KnowledgeId, normalized title, and an exact-delta digest; exclude timestamps, retries, agent/session IDs, and attempt numbers - if the user agrees, call
mcp__knowz__amend_knowledgewith the resolvedidand the delta payload. Send only the change, not a synthesized full body. - if the MCP call fails transiently, read
knowz-pending.mdand queue the amend once using the canonical fieldsOperation,Idempotency Key,Queue Status,KnowledgeId,Target Vault,Source, andPayload; an identical key/content is already queued, while a key collision fails closed
- call
- Never auto-save, never auto-amend, never store workflow handoffs, never block the main task, do not spawn helper reader/writer agents for this path, and do nothing if Knowz tools are unavailable.
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 · 34 lines · 44 tokens per session scan A dd9517eaeb3a
knowz-auto is a skill published in the GitHub repository knowz-io/deepseek-knowz-plugin (1 stars, last pushed 21d ago), licensed MIT. It adds 44 tokens to every session and 746 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 2026-08-31.
Other skills, from other repositories
krouter-obsidian
KRouter Obsidian — route knowledge-dependent tasks to the smallest current evidence set in an Obsidian vault using deterministic local search. Use when a request depends on durable user preferences, prior corrections or superseded claims, long-term project history or results, reusable methods or evidence, or the…
knowledge-wiki
Manage the personal knowledge wiki. Use when the user shares articles, documents, or asks to organize knowledge; when a conversation produces insights worth preserving as structured knowledge; or when the user asks about the knowledge base.
modlens
Plug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .heic, .heif) appears anywhere in the conversation (typed by the user, injected as a [Image: source: ] line, or inside a tag) and you cannot see that image's content, run this skill on it…
j-space
Use this skill to establish and operate the model's inner workspace — the J-space — for any task that needs more than fluent output: multi-step or chained reasoning, planning, long-horizon and agentic work, competition-level problems, complex debugging, keeping many parts of a deliverable globally consistent, holding…
install-openviking-memory
Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…
openviking-context-database
Use OpenViking from OpenClaw through @openviking/openclaw-plugin: long-term memory, session archives, resource and Agent Skill import, semantic recall, recall trace debugging, and externalized tool-result recovery. Prefer this skill when the user wants to use, query, debug, or operate OpenViking context from an…