loopflow ยท diff
git:20261027.142e096 to git:20261102.39defd0
13 added, 7 removed. Audit A to A.
---
name: loopflow
description: Hand changes off as Loopflow Tasks that each end in a pull request; check on, steer, resume and land them; run the repository's Skills and Graphs with lf.
---
# Work through lf
`lf` launches coding agents and keeps their sessions. Hand work off through it,
and keep this conversation free to talk.
## Hand off changes as Tasks
When the person asks for a change that should end in a pull request, make it a
Task and run it, one Task per reviewable outcome:
```bash
- lf task create --title "<outcome in the person's words>" # prints the Task ID
- lf task run <ID> # own worktree and branch; returns once running
- lf open --task <ID> --link --format markdown # the link to give back
+ lf task create <<'EOF' # prints the Task ID
+ <outcome in the person's words: the first line is the title>
+ EOF
+ lf task run <ID> # own worktree and branch; returns once running
+ lf open --task <ID> --link --format markdown # the link to give back
```
+ The person's words are data, never shell: send them on stdin through a quoted
+ heredoc as above, or as one single-quoted argument with each `'` written `'\''`.
+
Give back each Task's link and say what it will deliver. Questions, reading
code and one-line fixes the person wants here happen in this checkout, without
a Task. When unsure whether something is one Task or several, propose the split
and ask.
## Keep track
```bash
lf task list # open Tasks
lf task status <ID> # its run, its PR, what it needs from the person
- lf comment <ID> "<direction>" # reaches the run before its next step
+ lf comment <ID> '<direction>' # reaches the run before its next step
lf resume --task <ID> # the Task's conversation, for the person
lf land --wait-and-fix # only when the person asks to land
```
Report what status says. A finished run is not a merged PR, and a merged PR is
not a completed Task; say which happened.
## Skills and Graphs
- The repository's own Skills and Graphs come first. Find them with `lf list`,
- read one with `lf help <name>`, then run it: `lf <skill>` here, or
- `lf task run <ID> <graph>` on a Task.
+ Run a Skill or Graph only when the person asks for it, by name or by what it
+ does. They are the repository's own prompts and steps, so read one with
+ `lf help <name>` and say what it will do before running it: `lf <skill>` here,
+ or `lf task run <ID> <graph>` on a Task. `lf list` shows what exists.
## Boundaries
- Use the agent, account and machine the person names (`-a`, `--account`,
`--machine`); otherwise lf's defaults.
- One run per Task at a time: check `lf task status <ID>` before starting another.
- Never invent a Task identity or act on a Task nobody named.
- `lf help <command>` is the current reference; check it before using a command
for the first time. Docs: https://loopflow.studio/docs/agent-api.md