knowz-amend

knowz-amend is a skill for Claude Code, Codex from knowz-io/deepseek-knowz-plugin. It costs 59 tokens per session (935 once invoked), scanned A, original, MIT.

A targeted editing workflow for changing one existing item in a Knowz knowledge vault without rewriting the whole entry. A vault is a collection of stored knowledge items.

In plain words
What is it for?
Use it to amend an existing vault item by ID or by searching for its subject. For a completely new or fully rewritten entry, the input says to use the separate save workflow.
Why use it?
It preserves the parts that should stay unchanged and applies only the requested correction, addition, or tag change.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to amend an existing vault item by ID or by searching for its subject. For a completely new or fully rewritten entry, the input says to use the separate save workflow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/knowz-io/deepseek-knowz-plugin/knowz-amend
Install

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.

Any agent
npx skills add knowz-io/deepseek-knowz-plugin --skill knowz-amend
Clone the repo
git clone --depth 1 https://github.com/knowz-io/deepseek-knowz-plugin

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for knowz-amend

README.md
[![agentmods](https://agentmods.dev/badge/skills/knowz-io/deepseek-knowz-plugin/knowz-amend/github.svg)](https://agentmods.dev/skills/knowz-io/deepseek-knowz-plugin/knowz-amend)
Your own site
<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.

agentmods 80×15 button for knowz-amend

Your own site · 80×15
<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>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 935 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash ffbc61194ca4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

skills/knowz-amend/SKILL.md · 69 lines

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

  1. Read knowz-vaults.md from the project root if it exists.
  2. Parse the user's change from the request. Strip any --id <knowledgeId> flag and remember the value.
  3. Resolve the target item:
    • If --id was provided → call mcp__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 call mcp__knowz__search_knowledge scoped to the vault routing rules in knowz-vaults.md with limit: 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-save instead. Stop.
  4. Confirm the change with the user before writing:
    Amending in {Vault Name}:
      Title:  {existing title}
      Change: {user's requested change}
    
    Proceed only on explicit yes.
  5. Resolve one stable Idempotency Key from amend, 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.
  6. Call mcp__knowz__amend_knowledge with:
    • id: the resolved KnowledgeId
    • the delta payload that expresses the user's change. Do NOT send the full prior content.
  7. 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-save as the next step.
  8. If MCP write fails (server unreachable, auth expired), read knowz-pending.md first 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.

Read the full file on GitHub · 69 lines

Changes

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.

  1. 9d ago First seen · 69 lines · 59 tokens per session scan A ffbc61194ca4

Subscribe to this mod's changes

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.

Related

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…

398894496-arch/runtime36 · 85 tokens

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.

zhayujie/CowAgent · 46 tokens

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…

liustack/modlens · 240 tokens

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…

Tiger3807861189/J-Space-Cognition-Suite-V3.7 · 144 tokens

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…

volcengine/OpenViking · 191 tokens

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…

volcengine/OpenViking · 95 tokens