configure
Use when the user asks to set up or configure exo, or to see or change one exo setting, such as where specs go or the budget.
Skill by blauwtje
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/blauwtje-configure
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: finance
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/configure
Tools it pre-approves 11
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash(node*settings.mjs*),Bash(gitremoteget-urlorigin),rev-parse*),Bash(ghauthstatus)
What's inside
- Skill name
configure- Description
- Use when the user asks to set up or configure exo, or to see or change one exo setting, such as where specs go or the budget. Not for the harness's own settings.json, permissions or hooks.
- License
- MIT
- Allowed tools
- Bash(node, *settings.mjs*),, Bash(git, remote, get-url, origin),, Bash(git, rev-parse, *),, Bash(gh, auth, status)
- Instructions
- 66 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Pre-approves some shell commands
Files (4)
- SKILL.md
- setup-map.md · references/
- schema.json
- settings.mjs · scripts/
SKILL.md (first lines)
# Settings
Change exo's settings only through its own scripts, one named setting or every setting in one walk. The enemy is a value the user never picked: a guessed layer, or a walk that writes before its review. The overcorrection is a walk through every setting when the request named one.
## When to use
- `/exo:configure` with nothing after it, or request to set up or configure exo as a whole → `## The walk`.
- Question about one setting, or request to change one → `## One setting`.
## Where things stand
Values when this skill loaded, each with its layer:
!`node "${CLAUDE_SKILL_DIR}/scripts/settings.mjs" show`
## One setting
Take the first step the request and answers so far leave open.
- Answer a menu's `Or type` line names → counts as that pick, like its letter, at every step: topic, setting or value.
1. **Relay.** Request only asks to see the settings → relay the `show` block above as the whole reply, run nothing. Keep its ```` ```text ```` fence unchanged; rows line up only in a monospace block.
2. **Pick the setting.** Request names none → run `node "${CLAUDE_SKILL_DIR}/scripts/settings.mjs" menu`, relay its output unchanged as the whole reply.
- Topic picked → run `menu work`, `menu places` or `menu safety`, relayed the same way.
3. **Ask the value.** Setting known, no value → run `node "${CLAUDE_SKILL_DIR}/scripts/settings.mjs" menu <key>`, relay it the same way.
4. **Pick the layer.** Request names no layer → project scope: it reaches every collaborator, not only you, and only a named local or global layer changes that. The closing line names the layer used, so the choice is never hidden.
5. **Write** with the command `## The write commands` names, then run `show` and relay it under the script's confirmation line; the block above predates the change.
- Rejection → relay it as the script printed it, change nothing by hand.
- Project value → add one line under the fence: collaborators receive it once `.claude/exo.json` is committed.
## The walk
Follow `references/setup-map.md` from its first step. Never pick an answer for the user.
## The write commands
| Setting | Command |
|---|---|
| A key `show` lists, for this repository | `node "${CLAUDE_SKILL_DIR}/scripts/settings.mjs" set <key> <value> --scope <project or local>` |
| A key `show` lists, for every project | None: the harness owns that file. Report names the value to pick for that key under exo in `/config`. |
| The status line | `node "${CLAUDE_SKILL_DIR}/scripts/settings.mjs" statusline`; relay the printed `statusLine` block and its target file, edit no harness settings file. |
## References
| File | Read it when |
|---|---|
| `references/setup-map.md` | The walk, before its first step. Not for one setting. |
| `../route-skills/references/question.md` | Before a message that asks the user a question. |
## Judgment
- A project or local value outranks a global one.
- User picks every project for a key a project or local layer holds → report names that layer; the new value stays hidden there.
- Scripts' output outranks any value in context, including the session's `exo settings:` line, read at session start.
- Every delegate that writes code reads `../route-skills/references/lean.md` itself; the session text carries no pointer to it and no switch exists: request to switch it off → give that answer, run nothing.From blauwtje/exo, MIT.
More from blauwtje/exo
- 0.592score
file-issues
blauwtje
Use when the user types /exo:file-issues to file, open, write or split GitHub issues.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
ship
blauwtje
Use when commits may leave the machine, or the user asks to push, open, watch or merge a pull request or fix its failing checks, conflicts or review comments.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
spec
blauwtje
Use when a request leaves done, data, architecture or a trade-off open.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
start
blauwtje
Use when the user does not remember a skill's name, wants the list of exo skills in plain words, or names a goal and wants exo to pick.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
verify
blauwtje
Use when a plan's tasks are landed and its branch needs the gate before a pull request: the scripted checks, the branch review and its repairs.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
write-docs
blauwtje
Use when writing or editing prose read later: a README, doc page, PR, issue or commit body, changelog line, brief or spec.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
design-ui
blauwtje
Use when a page or component's look or copy changes, or looks empty, boring or generic.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
edit-skills
blauwtje
Use when creating, editing or sizing a skill or agent, and before it is done.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
find-cause
blauwtje
Use when reported wrong behavior (bug, error, crash, regression, slowdown) has no one-command repro, or its proof stays red after one plain fix attempt.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
improve
blauwtje
Use when the user invokes it to raise one score in a repo in an unattended loop, keeping a commit only when one fixed score command gets better and logging…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
prompt
blauwtje
Use when the user invokes it to rewrite a rough prompt into a grounded, tagged prompt for Claude and run it after approval.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
refactor
blauwtje
Use when a named refactor, rename, move or internal API reshape must keep behavior unchanged, or a shim or compatibility re-export tempts.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 6
- Last commit (this folder)
- Oct 23, 2026 (6 days ago)
- Last release
- Oct 19, 2026 (10 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/blauwtje/exo
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from blauwtje
- 0.592score
file-issues
blauwtje
Use when the user types /exo:file-issues to file, open, write or split GitHub issues.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
improve
blauwtje
Use when the user invokes it to raise one score in a repo in an unattended loop, keeping a commit only when one fixed score command gets better and logging…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
design-ui
blauwtje
Use when a page or component's look or copy changes, or looks empty, boring or generic.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
edit-skills
blauwtje
Use when creating, editing or sizing a skill or agent, and before it is done.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
find-cause
blauwtje
Use when reported wrong behavior (bug, error, crash, regression, slowdown) has no one-command repro, or its proof stays red after one plain fix attempt.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
prompt
blauwtje
Use when the user invokes it to rewrite a rough prompt into a grounded, tagged prompt for Claude and run it after approval.
SkillAFreshness: A★ 1Claude Code +9
Cite this page
configure skill. Agent Mart. https://agentmart.dev/skills/blauwtje-configure (last updated 2026-10-24)