Skip to content
Back to skills

Export

ASecurity

Bundle the canonical memory set into one structured Markdown document for external-LLM review, audit, or dashboard download.

  • 30 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 3, 2026
ai-agentsgit

Security analysis

A100/100

Scanned October 3, 2026

npx -y skills add fjwood69/mori --skill export --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Export?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Export
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fjwood69-export/badge)](https://www.skillsdirectory.com/skills/fjwood69-export)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: export
description: Bundle the canonical memory set into one structured Markdown document for external-LLM review, audit, or dashboard download.
---

**If the Mori server is unreachable** (a tool call returns a connection error, ECONNREFUSED, or timeout), do not show a stack trace. Tell the user the Mori server appears to be down and that a running Mori server is required. Point them to the quickstart at https://github.com/fjwood69/mori#quickstart and suggest checking the server URL in plugin settings. Then stop.

When the user runs `/export`, call `mori-export_canon` with the parsed arguments and present the result. Internal provenance/PII is stripped by the server by default — the export is safe to upload to an external model.

## Argument parsing

- `--project <name>` — filter to a project tag (e.g. `mori`, `bifrost`)
- `--type <type>` — filter by memory type (`decision`, `pattern`, `standard`, …)
- `--format <fmt>` — one of:
  - `standard` (default) — grouped, readable Markdown with a reproducibility pin header
  - `consult` — the same content prefixed by a **coherence-review rubric**, ready to paste into Kimi/Qwen/Opus (alongside `/consult`) for a canon audit
  - `json` — raw structured JSON
- `--output <path>` — write the result to a file instead of returning it inline
- `--include-working` — include working-tier memories as well as canonical

## Execution

1. Parse the arguments above.
2. Call `mori-export_canon` with `project` / `type` / `format` / `include_working`.
3. If `--output <path>` was given, write the returned string to that path and report the path + size; otherwise present the export directly.
4. For `--format consult`, tell the user it's ready to paste into an external model alongside `/consult` for a coherence audit (the rubric scores internal coherence — contradictions, redundancy, clarity — not whether claims match the live codebase).

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.