# Route

> Analyze an enriched note and route to the best vault destination. Stage 3 of the processing pipeline.

- **Type:** Skill
- **Install:** `agentstack add skill-technicalpickles-pickled-claude-plugins-route`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [technicalpickles](https://agentstack.voostack.com/s/technicalpickles)
- **Installs:** 0
- **Category:** [Security](https://agentstack.voostack.com/c/security)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [technicalpickles](https://github.com/technicalpickles)
- **Source:** https://github.com/technicalpickles/pickled-claude-plugins/tree/main/plugins/second-brain/skills/route

## Install

```sh
agentstack add skill-technicalpickles-pickled-claude-plugins-route
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Route Stage

Analyze an enriched note against routing memory, vault rules, and generic signals. Move to destination or mark for review.

See `references/pipeline.md` for stage definitions and status flow.
See `references/routing.md` for the scoring algorithm.
See `references/para.md` and `references/johnny-decimal.md` for the two folder systems a vault may use (often both, mid-migration).
See `references/routing-memory.md` for the correction and learning loop.

## Input

An enriched note in the inbox with `status: enriched`.

## Process

1. Load routing context:
   - Read `.routing-memory.md` from vault root (create with defaults if missing)
   - Read vault CLAUDE.md for disambiguation rules
   - Run `sb vault structure` for available destinations
   - Run `sb note context --note "{note-path}"` for keywords and signals

2. Score destinations (priority order):
   a. Check `.routing-memory.md` corrections for matching topics/keywords
   b. Check `.routing-memory.md` learned patterns
   c. Apply vault CLAUDE.md disambiguation rules
   d. Apply generic signal scoring (per `references/routing.md`)

   Each destination from `sb vault structure` carries a `type`. For Johnny Decimal destinations (`type: 'jd'`) also use `area` and `code` when scoring: match the note's topic to the `area`, and prefer an ID `code` (e.g. `67.01`) for a specific note or its parent category `code` (e.g. `67`) for a loose note. See `references/johnny-decimal.md`.

3. Apply threshold:
   - Score >= `auto-route-threshold`: auto-route, move file, set `status: routed`
   - Score < threshold: set `status: pending-review`, return without moving

4. If auto-routing, move the file:
   ```bash
   npx @techpickles/sb note move --from "{note-path}" --to "{destination}/"
   ```
   Update frontmatter: `status: routed`

5. If pending-review, present suggestions to human (when called by orchestrator):
   - Show top 2-3 destinations with scores and reasoning
   - Include "Leave in inbox" option
   - If user overrides suggestion, capture correction to `.routing-memory.md`

## Capturing Corrections

When the user picks a destination different from the top suggestion:

1. Ask: "Quick note on why {chosen} over {suggested}?"
2. Append to `## Corrections` in `.routing-memory.md`:
   ```
   - {YYYY-MM-DD}: "{note title}" routed to "{suggested}", corrected to "{chosen}"
     Reason: {user's reason}
   ```
   For Johnny Decimal destinations, key the correction on the JD `code` (e.g. "corrected to 67.01") so the learning loop can match by number, not just folder name.

## Output

- Note moved to destination with `status: routed`, OR
- Note marked `status: pending-review` for human input

## Constraints

- Only suggest destinations from `sb vault structure` output
- Always include "Leave in inbox" for pending-review notes
- Show reasoning for all suggestions
- Capture corrections on every override (this is how routing improves)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [technicalpickles](https://github.com/technicalpickles)
- **Source:** [technicalpickles/pickled-claude-plugins](https://github.com/technicalpickles/pickled-claude-plugins)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-technicalpickles-pickled-claude-plugins-route
- Seller: https://agentstack.voostack.com/s/technicalpickles
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.