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 agentmods add skills/knowz-io/deepseek-knowz-plugin/knowz-savenpx skills add knowz-io/deepseek-knowz-plugin --skill knowz-savegit 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-save)<a href="https://agentmods.dev/skills/knowz-io/deepseek-knowz-plugin/knowz-save"><img src="https://agentmods.dev/badge/skills/knowz-io/deepseek-knowz-plugin/knowz-save.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 | $0.00041 | $0.00953 |
| Opus 5 | $0.00020 | $0.00477 |
| Sonnet 5 | $0.00008 | $0.00191 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
knowz-save 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 6d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/knowz-save — Capture knowledge
Save a durable insight to the correct Knowz vault.
If enterprise.json exists in the project root, use its brand value instead of "Knowz" in user-facing text.
Instructions
- Read
knowz-vaults.mdfrom the project root if it exists. - Parse the content the user wants to save.
- Perform reads and writes directly from the current agent. Do not assume delegated writer agents.
- Classify the capture:
- pattern/reusable/utility → Pattern
- chose/decided/trade-off → Decision
- workaround/limitation/temporary → Workaround
- faster/optimized/cache → Performance
- security/vulnerability/auth → Security
- always/never/standard/convention → Convention
- otherwise → Note
- Route to the best vault using
When to saverules.- Multiple strong matches → ask the user to choose.
- No match → use the default vault when available.
- Expand terse input into a self-contained body:
[CONTEXT] Where and why this arose [INSIGHT] The reusable knowledge [RATIONALE] Why this approach or decision won [TAGS] category, technology, domain keywords - Generate a title in the form
{Category}: {Descriptive summary}. - Run a dedupe check with
mcp__knowz__search_knowledgeusing the title and target vault. If there is a close match, offer the user four choices:- Create anyway — new, separate entry
- Skip — don't save
- Amend existing item — apply a targeted delta (add a line, fix a phrase, change a tag). Preferred for partial changes.
- Replace existing item — full rewrite with a complete new body
- Resolve one stable
Idempotency Keybefore the mutation. Derive it from the chosen operation, resolved target vault, matchedKnowledgeIdor semantic identity when present, normalized title, and a digest of the exact payload. It MUST NOT contain a timestamp, retry count, agent/session ID, or attempt number. Reuse the same key if the response is lost or the operation is retried. - Execute the chosen path:
- Create (default, no dedupe match, or "Create anyway"): call
mcp__knowz__create_knowledgewithknowledgeType: "Note", the chosenvaultId, and tags. - Amend: call
mcp__knowz__amend_knowledgewithid= the matched item's ID and the delta payload. Send only the change, not a synthesized full body. - Replace: call
mcp__knowz__update_knowledgewithid= the matched item's ID and the complete new payload. - Skip: report that nothing was saved and stop.
- If MCP write fails, read
knowz-pending.mdfirst, then append a capture block using the canonical format only when the same key/content is absent. The same key with different mutation content is a collision and MUST fail closed. Wrap the block in---delimiters — the flush parser splits on them.
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.
- 6d ago First seen · 69 lines · 41 tokens per session scan A 567180f80b80
knowz-save is a skill published in the GitHub repository knowz-io/deepseek-knowz-plugin (1 stars, last pushed 20d ago), licensed MIT. It adds 41 tokens to every session and 953 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…