kg

kg is a command for coding agents from johnnywuj81/tokenknows. It costs 54 tokens per session (403 once invoked), scanned A, original, MIT.

A command that turns the current session into a knowledge graph: a visual map of people, events, concepts, and artifacts linked by relationships. It is designed for conversations involving several people, decisions, documents, or tools.

In plain words
What is it for?
Use it for cross-team reviews, project wrap-ups, incident investigations, and other relationship-heavy sessions, then explore the result in a browser.
Why use it?
It makes relationships and dependencies easier to see than a linear conversation. It can also help trace causes in incident reviews and find where an entity appears across documents.

Command

Part of the tokenknows plugin — 2 skills, 9 commands, 1 MCP server shipped together

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.

agentmods
npx agentmods add commands/johnnywuj81/tokenknows/kg
Clone the repo
git clone --depth 1 https://github.com/johnnywuj81/tokenknows

Or install tokenknows, the plugin that ships this one along with the rest of its 2 skills, 9 commands, 1 MCP server.

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 kg

README.md
[![agentmods](https://agentmods.dev/badge/commands/johnnywuj81/tokenknows/kg.svg)](https://agentmods.dev/commands/johnnywuj81/tokenknows/kg)
Your own site
<a href="https://agentmods.dev/commands/johnnywuj81/tokenknows/kg"><img src="https://agentmods.dev/badge/commands/johnnywuj81/tokenknows/kg.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 403 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00054 $0.00403
Opus 5 $0.00027 $0.00201
Sonnet 5 $0.00011 $0.00081
Haiku 4.5 $0.00005 $0.00040

Measured 3d ago against content hash 63dd8aae1612, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kg 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 3d 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.

tokenknows-plugin/commands/kg.md · 26 lines

What it actually says

tokenknows:distill skill 的标准流程,把当前 session 蒸馏成 knowledge_graph:

KG 关键价值:

  • 跨实体关系一目了然 (谁推动了什么 / 什么依赖什么 / 哪些决策冲突)
  • 跨文档实体合并 (Alice 在多个 KG 里自动合一)
  • 浏览器内可视化拖拽探索

适合用 KG 的对话:

  • 涉及 多人, 多决策, 多文档/工具
  • 故障复盘 + 后续修复 (caused_by 链)
  • 季度回顾 / 大项目 wrap-up
  1. 拆 event 时给每个实体清晰锚定 (谁 / 什么时候 / 做了什么) - 后端会基于此抽节点
  2. submit_session_events
  3. distill_document(document_type="knowledge_graph", time_window=$ARGUMENTS 默认 last_30_days)
  4. 轮询完成
  5. 展示:
    • 节点数 / 边数 / 4 类节点分布
    • 用 ASCII art 示意一两条关键关系 (e.g. Alice --authored_by--> PR#127 --depends_on--> retry_jitter)
    • 给浏览器 URL 让用户看完整可视化 (view_url 是绝对 URL, 前缀由 TOKENKNOWS_WEB_BASE 决定; 需登录 Web 工作台)
  6. 如果用户问 "X 在哪些文档里也出现", 调 search_entity(query="X")
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. 3d ago First seen · 26 lines · 54 tokens per session scan A 63dd8aae1612

Subscribe to this mod's changes

kg is a command published in the GitHub repository johnnywuj81/tokenknows (4 stars, last pushed 15d ago), licensed MIT. It adds 54 tokens to every session and 403 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.