flow-config
Display the current FLOW configuration from .flow.json — version and per-skill autonomy settings.
12 stars
Best use case
flow-config is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Display the current FLOW configuration from .flow.json — version and per-skill autonomy settings.
Teams using flow-config should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
$curl -o ~/.claude/skills/flow-config/SKILL.md --create-dirs "https://raw.githubusercontent.com/benkruger/flow/main/skills/flow-config/SKILL.md"
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/flow-config/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How flow-config Compares
| Feature / Agent | flow-config | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Display the current FLOW configuration from .flow.json — version and per-skill autonomy settings.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# FLOW Config — Display Configuration
## Usage
```text
/flow:flow-config
```
Display-only skill. Reads `.flow.json` from the project root and shows the current configuration.
## Steps
### Step 1 — Read config
Use the Glob tool to check for `.flow.json` at the project root.
If `.flow.json` does not exist, tell the user:
> "No `.flow.json` found. Run `/flow:flow-prime` to configure this project."
Stop here.
If `.flow.json` exists, read it with the Read tool.
### Step 2 — Display config
Output the following banner in your response (not via Bash) inside a fenced code block:
````markdown
```text
──────────────────────────────────────────────────
FLOW v<version> — Config
──────────────────────────────────────────────────
```
````
Then display the skills configuration as a markdown table:
```text
| Skill | Commit | Continue |
|-----------|--------|----------|
| start | — | manual |
| code | manual | manual |
| review | auto | auto |
| learn | auto | auto |
| complete | — | auto |
| abort | — | auto |
```
Use the actual values from `.flow.json`. The table above is just an example.
**Column rules:**
- **Skills with both axes** (code, review, learn): show both `commit` and `continue` values from the nested object
- **Skills with continue only** (start, complete, abort): show `—` for Commit, show the `continue` value from the nested object
**Legacy format handling:** If `.flow.json` has the old single-value format (e.g., `"code": "manual"` instead of `{"commit": "manual", "continue": "manual"}`), display the single value in both columns for phase skills that should have two axes.
If `.flow.json` has no `skills` key, show "No skills configured — using built-in defaults" instead of the table.
Tell the user that autonomy is configured in `.flow.json` — there are no `--auto`/`--manual` invocation flags — and that re-running `/flow:flow-prime` changes it.
## Hard Rules
- Display only — never modify `.flow.json`
- Never use Bash to print banners — output them as text in your response
- Never use Bash for file reads — use Glob, Read, and Grep tools instead of ls, cat, head, tail, find, or grep
- Never use `cd <path> && git` — use `git -C <path>` for git commands in other directories
- Never cd before running `bin/flow` — it detects the project root internallyRelated Skills
We are still matching the closest adjacent skills for this page. In the meantime, continue through the full directory.