← ClaudeAtlas

ingestlisted

Bootstraps the memory store from existing material (repos, PDFs, transcripts). Use to seed memory from a project or document.
fjwood69/mori · ★ 19 · AI & Automation · score 75
Install: claude install-skill fjwood69/mori
## Filesystem mode (server-local paths) 1. If the user passes `--status`, call `mori-ingest_status` and present the table. 2. If the user passes `--preview` or `--dry-run` with no source provided, remind them to provide `--source <path>`. 3. For `--preview`: call `mori-ingest_preview` with the `--source` path(s) and any `--type` or `--since` arguments. Present the chunk breakdown and cost estimate. Remind the user this is zero-cost — no LLM was called. 4. For `--dry-run`: call `mori-ingest` with `dry_run=true` and all provided arguments. Report what would be written and the actual cost incurred (the LLM was called, just nothing committed). 5. For a real ingestion run: call `mori-ingest` with all provided arguments. Report: sources processed, chunks sent, memories written, cost estimate, errors. 6. If errors occurred for specific files, report them individually. 7. After successful ingestion, suggest running `/brief` to reload shared memories so the new entries are visible. 8. For large or expensive-looking sources, suggest `/ingest --preview` first to check before committing. ## Content mode (remote clients — HTTP upload) When the user passes `--content <path>`, upload the file directly to the mori-ingestion pod. Do NOT use the `mori-ingest_content` MCP tool — it has been removed. Use HTTP multipart upload only. Requires: - `MORI_INGEST_URL` env var (set by installer — NOT derived from `MORI_URL`) - `MORI_API_KEY` env var (same key as MCP auth) ### Linux/macOS ```bash J