# pagelore

> pagelore — krowli-pagelore. Use this tool when you need to maintain a durable project memory for AI coding agents, storing decisions and bug post-mortems as markdown pages in your repository. It solves problems of knowledge loss and reproducibility by providing a searchable record of project history through BM25F search via CLI or MCP server. It takes markdown pages as input and outputs searchable project knowledge, ideal for use in git-based projects.

Canonical page: https://skillsregistry.net/skills/krowli-pagelore  
JSON: https://api.skillsregistry.net/v1/skills/krowli-pagelore

## Description

Durable project memory for AI coding agents (Claude Code, Codex, Cursor, Gemini CLI): decisions and bug post-mortems as markdown pages in your repo, BM25F search via CLI or MCP server, validated writes. No server, no database, stdlib-only Python.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## 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/Krowli/pagelore)

## 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": "krowli-pagelore"
    }
  }
}
```

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