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-amendgit 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-amend)<a href="https://agentmods.dev/skills/knowz-io/deepseek-knowz-plugin/knowz-amend"><img src="https://agentmods.dev/badge/skills/knowz-io/deepseek-knowz-plugin/knowz-amend/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/knowz-io/deepseek-knowz-plugin/knowz-amend"><img src="https://agentmods.dev/badge/skills/knowz-io/deepseek-knowz-plugin/knowz-amend.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.00935 |
| Opus 5 | $0.00030 | $0.00467 |
| Sonnet 5 | $0.00012 | $0.00187 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
knowz-amend 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 9d 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-amend — Targeted vault edit
Patch an existing Knowz knowledge item with just the change the user describes. Prefer this over /knowz-save + "Replace existing" whenever the change is partial — amend_knowledge preserves untouched fields server-side and does not require the user to retype the whole entry.
If enterprise.json exists in the project root, use its brand value instead of "Knowz" in user-facing text.
Routing
If the user hands over a complete new body or explicitly asks to "replace" or "rewrite" the entry, use /knowz-save with "Replace existing item" instead — that path calls update_knowledge.
If the target item does not exist yet, use /knowz-save — amend cannot create new items.
Instructions
- Read
knowz-vaults.mdfrom the project root if it exists. - Parse the user's change from the request. Strip any
--id <knowledgeId>flag and remember the value. - Resolve the target item:
- If
--idwas provided → callmcp__knowz__get_knowledge_item(id)to confirm the item exists and fetch its title + vault for the confirmation step. - If no
--id→ extract the subject of the change and callmcp__knowz__search_knowledgescoped to the vault routing rules inknowz-vaults.mdwithlimit: 5.- One clear match → use it.
- Multiple plausible matches → present the top 3 with titles and snippets and ask the user which one.
- Zero matches → report no matching item was found and suggest
/knowz-saveinstead. Stop.
- If
- Confirm the change with the user before writing:
Proceed only on explicit yes.Amending in {Vault Name}: Title: {existing title} Change: {user's requested change} - Resolve one stable
Idempotency Keyfromamend, the resolved target vault,KnowledgeId, normalized title, and a digest of the exact delta. It MUST NOT contain a timestamp, retry count, agent/session ID, or attempt number. Reuse it for every retry. - Call
mcp__knowz__amend_knowledgewith:id: the resolved KnowledgeId- the delta payload that expresses the user's change. Do NOT send the full prior content.
- If the server reports the target is missing (deleted concurrently, bad id): do NOT silently fall through to create a new item. Report the missing-target conflict and offer
/knowz-saveas the next step. - If MCP write fails (server unreachable, auth expired), read
knowz-pending.mdfirst and append a canonical block 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.
- 9d ago First seen · 69 lines · 59 tokens per session scan A ffbc61194ca4
knowz-amend is a skill published in the GitHub repository knowz-io/deepseek-knowz-plugin (1 stars, last pushed 23d ago), licensed MIT. It adds 59 tokens to every session and 935 once invoked, about $0.0003 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…