Skip to content
Skills Library
Programming · Analysis

run

/run

Use when starting, following or explaining an Ork run - what it's doing, why it failed, what it cost, and what waits on the person - and when the person asks about their Ork runs.

Repository
ork ↗
Licence
MIT
Last repository change
13.11.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 13.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use when starting, following or explaining an Ork run - what it's doing, why it failed, what it cost, and what waits on the person - and when the person asks about their Ork runs.

Original author description

Use when starting, following or explaining an Ork run - what it's doing, why it failed, what it cost, and what waits on the person - and when the person asks about their Ork runs.

How it works

  1. Starting
  2. Following
  3. What only the person does
  4. Without Ork's tools
Original SKILL.md headings · 55 lines, 399 words
SKILL.md preview
---
name: run
description: Use when starting, following or explaining an Ork run - what it's doing, why it failed, what it cost, and what waits on the person - and when the person asks about their Ork runs.
---

# Running and following Ork workflows

Ork runs workflows on the person's machine with their accounts, so a run spends
their money and can push, merge or deploy. Start one only when they ask, and
never answer a decision for them.

## Starting

1. Find it: Ork's `workflows` tool gives each workflow's name and inputs.
2. Check it first with `check` (`workflow: <name>`). Don't start one with an
   error.
3. Start it with `start_run`, giving every required input. Claude Code asks the
   person first, unless they've allowed it. It answers with the run's id; the run goes on in the
   background, whatever happens to this conversation.

Without Ork's tools: `ork run <workflow> --detach --input name=value`.

## Following

- `run` gives a run's status, what it waits on, its cost so far, and each
  node's state. `runs` lists the newest runs.
- `run_events` gives its newest events; `node` narrows them, and `last` or
  `after` widens them. A `node.finished` event with `ok: false` says why a node
  failed.
- `explain_context` says what a node's session was given: its agent,
  instructions, skills and files. Use it when a node didn't know something.
- `usage` says what runs spent, by workflow and model, and how close the limits
  are.

Say what you found plainly: which node, what it said, and what it cost. Quote a
node's own words rather than retelling them.

## What only the person does

- **Decisions.** `decisions` lists the questions waiting on them: a gate, a loop
  that ran out of rounds, a permission. Tell them what each asks, the options,
  and the recommended one, and that they answer in `ork ui` or with
  `ork decide` in their own terminal. Don't answer one: never run
  `ork decide --id … --choose …`; with Ork's plugin, a hook stops it.
- **Stopping, pausing, resuming.** Tell them the command: `ork stop <run>`,
  `ork pause <run>`, `ork continue <run>`, `ork resume <run>`. A node can be
  stopped alone with `--node <id>`.

## Without Ork's tools

| Want                   | Command                        |
| ---------------------- | ------------------------------ |
| Runs, newest first     | `ork ps`                       |
| A run's transcript     | `ork logs <run>` (`--follow`)  |
| Its nodes and cost     | `ork tree <run>`               |
| What runs spent        | `ork usage`                    |
| What waits on a person | `ork decide --list`            |
| A node's context       | `ork context explain <wf> <n>` |

Versions

RepositoryScoreLicence
This page · mimshins/ork90MIT
phnx-labs/agi-cli100Apache-2.0
Insilico-org/plsi100MIT
jtsternberg/claude-plugins100MIT
jameskomo/config-drift-checker100Apache-2.0
lucastamoios/skills100MIT
andriiklymiuk/corgi100MIT
lucastamoios/skills100MIT
Dinusha-Ekanayake/specsteward100MIT

Database snapshot: 13.11.2026 · package version 8809986e02dd (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100write
    Use when writing or changing an Ork workflow (a `.ork/workflows/*.ork.yaml` file) - its nodes, edges, conditions and loops - and checking each draft until Ork accepts it.
  • 100setup
    Use when the person asks you to set up Ork, install it, or get started with it in a repository - checking it's installed, setting up the project, making Ork's tools available to you, and a first workflow.
  • 100implement
    Full-power feature implementation using parallel subagents for backend, frontend, testing, and security, with worktree isolation and quality verification in one workflow. Chains with /ork:cover for tests and /ork:verify for validation. Use when asked to build, add, create,…
  • 100design-ship
    One-shot pipeline turning a claude.ai/design link into a pull request: scaffold via /ork:design-import, stories and specs via /ork:cover, browser verification via /ork:expect, then open the PR. Use when a design link should come back as a PR with no intermediate steps; if all…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.