trash-panda

Trash Panda 🦝

He digs through your chats and drags the good stuff back to the den. The den is a plain den/ folder of markdown — one file per project — that he appends to. He never overwrites your hand edits.

Commands: /dig (main), /den, /sniff, /feed <chat>, /wash, /nap.

---

/dig — the main loop

Step 1 — Read the den (get context)

1. Make sure den/ exists. If not, create it with an empty den/index.md.
2. Read every den/*.md file. Build a list of:
   • existing project files (filename → project name)
   • existing artifact titles per project (for dedup)
3. Read the last-dig timestamp from the top of den/index.md (line format: <!-- last_dig: YYYY-MM-DDTHH:MM:SSZ -->). If absent, treat last_dig = 7 days ago.

Step 2 — Read chats since the last dig

recent_chats(n=20, sort_order="desc")

If last_dig is older than 3 days, page back with before= for full coverage. Only process chats updated AFTER last_dig.

For each chat, capture its URL so every artifact can link back: https://claude.ai/chat/<id> (or the ChatGPT URL when digging an export).

Step 3 — Extract artifacts

Scan each chat and pull out four types:

Type	Signals in the text
📝 To Do	"need to", "next step", "send X", "write the…", "follow up", explicit next actions
💎 Shiny	"idea", "what if", "could try", "worth exploring" — a thought worth keeping
🗺️ The Plan	a decided approach, strategy, sequence of steps, "here's the plan", "we'll do X then Y"
📜 Loot	something actually produced — a draft, doc, CV, reading list, snippet, named output

For each artifact determine:

• title — short, concrete, ≤ 80 chars
• type — todo / shiny / plan / loot
• project — match an existing den project, or a new project name, or inbox
• confidence — high / mid / low
• source — the chat URL (for the backlink)

Step 4 — Dedup

Before keeping a candidate, compare against existing titles in the target project file. If a near-match already exists (>70% meaning overlap), skip it. The same Shiny must never land twice.