# tokenknows

> tokenknows — johnnywuj81-tokenknows. Use this tool when you need to organize and summarize AI coding sessions into actionable insights and reports. Tokenknows solves the problem of information overload by distilling sessions into weekly reports, ADRs, incident reviews, and a knowledge graph, providing a local-first and evidence-linked interface. It takes in git data and outputs structured reports and a knowledge graph, ideal for use in software development and project management contexts.

Canonical page: https://skillsregistry.net/skills/johnnywuj81-tokenknows  
JSON: https://api.skillsregistry.net/v1/skills/johnnywuj81-tokenknows

## Description

Distill AI coding sessions (Claude Code / Codex / Cursor) into weekly reports, ADRs, incident reviews and a knowledge graph — local-first, evidence-linked.

## Trust

- **Trust score (0–1):** 0.46
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/johnnywuj81/tokenknows)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "johnnywuj81-tokenknows"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/johnnywuj81-tokenknows` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/johnnywuj81-tokenknows/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt