> ## Documentation Index
> Fetch the complete documentation index at: https://docs.orinadus.com/llms.txt
> Use this file to discover all available pages before exploring further.

# urchin collect

> Run a collector once and append new events to the journal.

## Synopsis

```bash theme={null}
urchin collect <COLLECTOR> [OPTIONS]
```

## Subcommands

### shell

```bash theme={null}
urchin collect shell
```

Tails `~/.bash_history` from the last recorded byte offset. New lines are ingested as `command` events with `source: "shell"`. A checkpoint file at `~/.local/share/urchin/shell.checkpoint` tracks the offset so reruns are incremental.

No-op if `~/.bash_history` does not exist.

***

### git

```bash theme={null}
urchin collect git --repo <PATH> [--repo <PATH> ...]
```

<ParamField path="--repo" type="string" required>
  Absolute path to a git repository root. Repeatable. Can also be supplied via the `URCHIN_REPO_ROOTS` environment variable (colon-separated paths).
</ParamField>

Reads new commits since the last recorded SHA for each repo. Ingests each commit as a `commit` event with the commit message as `content`, commit SHA in `title`, and `source: "git"`. Per-repo checkpoints are stored in `~/.local/share/urchin/git-<hash>.checkpoint`.

First run per repo is silent — it records the current HEAD but does not ingest historical commits.

```bash theme={null}
urchin collect git --repo /home/user/dev/myproject

# Or via env var:
export URCHIN_REPO_ROOTS=/home/user/dev/myproject:/home/user/dev/other
urchin collect git
```

***

### claude

```bash theme={null}
urchin collect claude
```

Reads `~/.claude/projects/` JSONL transcript files. Ingests new conversation turns as `conversation` events with `source: "claude"`. Uses file + line-offset checkpoints.

***

### copilot

```bash theme={null}
urchin collect copilot
```

Reads `~/.copilot/command-history-state.json`. Uses a content-addressed hash checkpoint — reruns only ingest entries that weren't present in the previous run.

***

### gemini

```bash theme={null}
urchin collect gemini
```

Reads `~/.gemini/tmp/*/chats/*.jsonl`. Partial-offset checkpoint per file.

***

### codex

```bash theme={null}
urchin collect codex
```

Reads `~/.codex/state_5.sqlite`, `threads` table. Captures `first_user_message` as intent. Row ID watermark checkpoint.

***

### opencode

```bash theme={null}
urchin collect opencode
```

Reads `~/.local/share/opencode/opencode.db`. JOINs messages with sessions, filters to user-role messages. Row ID watermark checkpoint.

***

### local-model

```bash theme={null}
urchin collect local-model
```

Reads `~/.local/share/urchin/local-model.jsonl`. Any local inference harness (Ollama, LM Studio, llama.cpp) can push events by appending newline-delimited JSON to this file:

```json theme={null}
{"prompt":"fix the memory leak","model":"ollama:mistral","ts":"2026-05-01T10:00:00Z","workspace":"/opt/project"}
```

Fields: `prompt` (required), `model` (optional), `ts` (RFC3339, optional), `workspace` (optional). Urchin reads from this file and never writes to it. No-op when the file does not exist.

***

### all

```bash theme={null}
urchin collect all
```

Runs every collector that has a discoverable default path: shell, git (via `URCHIN_REPO_ROOTS`), claude, copilot, gemini, codex, opencode, local-model.

Collectors whose source path does not exist are silently skipped.

## Notes

* All collectors are read-only. They never write back to source tools.
* Each collector is idempotent — running it twice produces no duplicate events.
* Collector errors are printed to stderr but do not affect other collectors when running `all`.