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-setupnpx skills add knowz-io/deepseek-knowz-plugin --skill knowz-setupgit 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-setup)<a href="https://agentmods.dev/skills/knowz-io/deepseek-knowz-plugin/knowz-setup"><img src="https://agentmods.dev/badge/skills/knowz-io/deepseek-knowz-plugin/knowz-setup.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 | $0.00041 | $0.00936 |
| Opus 5 | $0.00020 | $0.00468 |
| Sonnet 5 | $0.00008 | $0.00187 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
knowz-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/knowz-setup — Connect and map vaults
Configure hosted Knowz MCP for DeepSeek Harness, then write project vault routing.
Auth is KNOWZ_API_KEY (a ukz_ key from https://app.knowz.io/settings/api-keys). There is no DeepSeek store and no Authorize card on this host.
Primary install (do this first)
If Knowz tools such as mcp__knowz__list_vaults are already available, skip to Create or refresh vault routing.
Otherwise tell the user to connect the plugin — do not paste API keys in chat.
DeepSeek Harness
- Create a
ukz_key at https://app.knowz.io/settings/api-keys - Set
KNOWZ_API_KEYin the environment or$DSH_HOME/.credentials.yaml(export KNOWZ_API_KEY=ukz_…). Do not paste the key in chat. - Install if needed:
dsh plugin --profile web add github:knowz-io/deepseek-knowz-plugin. Local first-slice from the source monorepo:dsh plugin --profile web add ./hosts/deepseek/plugins/knowz. Official discovery is the GitHub topicdsh-plugin. There is no DeepSeek store. - Restart
dsh web.
Do not run /knowz register when the user already has a Knowz account — that path creates a new account. /knowz register is not login.
Do not paste API keys in chat. The shipped MCP row interpolates process.env.KNOWZ_API_KEY into Authorization: Bearer. Export + restart is the path that attaches the header.
For a second Knowz tenant (personal + business): two MCP rows with unique serverName values and two env refs. Same URL https://mcp.knowz.io/mcp is fine. Duplicate serverName fails at load.
Endpoint
Use https://mcp.knowz.io/mcp unless the project root has enterprise.json with mcp_endpoint. --dev may use https://mcp.dev.knowz.io/mcp. --endpoint <url> overrides.
Create or refresh vault routing
Generate knowz-vaults.md at the project root if it does not already exist. This file drives vault routing for /knowz-search, /knowz-ask, /knowz-browse, and /knowz-save.
- Call
mcp__knowz__list_vaultsto discover available vaults. - For each vault, write a section:
- ID — the vault id from the server
- Description — what the vault stores
- When to query — situations that should fan out to this vault
- When to save — situations that should write to this vault
- Content template —
[CONTEXT] / [INSIGHT] / [RATIONALE] / [TAGS]
- Set a Default vault at the bottom for cases that match no rule.
- Add a Trust & Freshness section: vault entries are point-in-time and may be stale — treat them as leads to verify against the live codebase, tests, and current docs.
- Do not invent fields; if information is missing, leave the section short.
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.
- 4d ago First seen · 59 lines · 41 tokens per session scan A 31f6e8da4f2b
knowz-setup is a skill published in the GitHub repository knowz-io/deepseek-knowz-plugin (1 stars, last pushed 19d ago), licensed MIT. It adds 41 tokens to every session and 936 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…
dsh-archive-agent-notes
Use when adding, auditing, pruning, archiving, restoring, or reviewing Agent Notes in deepseek-harness; checks every new note for superseded active records, classifies implemented notes by future decision value, deletes rejected notes that no longer prevent a tempting fallacy, and applies the frozen archived/{kind}…
dsh-archive-agent-notes
Use when adding, auditing, pruning, archiving, restoring, or reviewing Agent Notes in deepseek-harness; checks every new note for superseded active records, classifies implemented notes by future decision value, deletes rejected notes that no longer prevent a tempting fallacy, and applies the frozen archived/{kind}…
dsh-archive-agent-notes
Use when adding, auditing, pruning, archiving, restoring, or reviewing Agent Notes in deepseek-harness; checks every new note for superseded active records, classifies implemented notes by future decision value, deletes rejected notes that no longer prevent a tempting fallacy, and applies the frozen archived/{kind}…
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…