A Claude plug-in that turns a coding session into structured documents through a self-hosted service. It can produce weekly reports, technical plans, architecture decision records, retrospectives, books, skills, and knowledge graphs.

Use it to distill a session into project documentation or a knowledge graph. It requires the TokenKnows backend, web workspace, and uv setup.

It organizes scattered session details into reusable written knowledge instead of leaving decisions and lessons buried in chat.

tokenknows — Plugin for Claude Code by johnnywuj81

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.

Clone the repo

git clone --depth 1 https://github.com/johnnywuj81/tokenknows

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/johnnywuj81/tokenknows/tokenknows-plugin/github.svg)](https://agentmods.dev/plugins/johnnywuj81/tokenknows/tokenknows-plugin)

Your own site

<a href="https://agentmods.dev/plugins/johnnywuj81/tokenknows/tokenknows-plugin"><img src="https://agentmods.dev/badge/plugins/johnnywuj81/tokenknows/tokenknows-plugin/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/johnnywuj81/tokenknows/tokenknows-plugin"><img src="https://agentmods.dev/badge/plugins/johnnywuj81/tokenknows/tokenknows-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 2 skills, 9 commands, 1 MCP server cost 540 tokens a session between them.

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.

Security

Grade A, and why

tokenknows 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 1mo 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/.claude-plugin/plugin.json · 20 lines

What it actually says

{
  "name": "tokenknows",
  "version": "2.2.0",
  "description": "把当前 Claude session 蒸馏成结构化文档 (周报 / 技术方案 / ADR / 复盘 / 书籍 / Skill / 知识图谱), 通过 MCP 接 tokenknows-api 后端 5-stage pipeline. 前置: 自托管后端 + Web 工作台 + uv, 详见 README.",
  "author": {
    "name": "TokenKnows",
    "url": "https://github.com/johnnywuj81/tokenknows"
  },
  "homepage": "https://github.com/johnnywuj81/tokenknows/tree/main/tokenknows-plugin",
  "repository": "https://github.com/johnnywuj81/tokenknows",
  "license": "MIT",
  "keywords": [
    "knowledge-distill",
    "weekly-report",
    "adr",
    "knowledge-graph",
    "mcp"
  ]
}

Contents

What it installs

The manifest is a name and a version. 2 skills, 9 commands, 1 MCP server travel with it, and installing the plugin installs all of them — 540 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

1mo ago First seen · 20 lines scan A cc6e443cbd49

Subscribe to this mod's changes

tokenknows is a plugin published in the GitHub repository johnnywuj81/tokenknows (4 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Claude Code Documents Writing and docs ai-agents codex cursor developer-tools fastapi

anthropic-office-skills

Official Anthropic skills for PDF, Word, PowerPoint, and Excel files.

fcakyon/claude-codex-settings · not measured

paperfit

Vision-in-the-loop LaTeX visual typesetting optimization (VTO) — agents, skills, and slash commands for Claude Code.

OpenRaiser/PaperFit · not measured

business

Business — 11 free skills bundled together.

lovstudio/skills · not measured

xlsx-for-ai

Recalculate spreadsheet formulas, check a sheet for errors, and write real .xlsx files from Claude. Use it when the answer depends on formula results, on whether saved values are current, or on handing back a working spreadsheet file. Your spreadsheet files are sent to the hosted xlsx-for-ai server for processing.

senoff/xlsx-for-ai · not measured

falconer

Read, search, and update Falconer documents from Claude Code through hosted HTTP MCP.

FalconerAI/agent-integrations · not measured

presentation-md

Notes → schema-crafted deck in Claude Code. /slides slash, 75 themes, MCP craft gates, editable PowerPoint. Install: npx @presentation-md/install claude-code or /plugin marketplace add isatimur/presentation-md.

isatimur/presentation-md · not measured