How do I install the Harness Mint skill?

Run npx skillmds@latest add gabrielmoreira/harness-mint in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Harness Mint safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Harness Mint?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Harness Mint free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Harness Mint?

gabrielmoreira (@gabrielmoreira) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Harness Mint by gabrielmoreira — Agent Skill

Name: Harness Mint
Rating: 4.666666666666667 (3 reviews)
Author: gabrielmoreira

Harness Mint

Scaffold a custom AI agent harness via `metaharness new <name> --template <id> --host <id>`. Defaults to DRY-RUN (no writes) unless --confirm is passed. Refuses to write to the calling repo root or anywhere inside it. Honors ADR-150 architectural constraint + ruflo's "destructive-action confirmation" pattern.

gabrielmoreira Updated Sep 9, 2026 17 repo stars

File contents

The one write-capable skill in the plugin. Every other skill is pure-read. This one calls metaharness new, which writes a new directory tree.

Safety (load-bearing)

Dry-run by default. Without --confirm, the script prints what it would do and exits 0 without touching disk.
Refuses project root. If --target resolves to the current working directory OR any path inside it, the script errors out with exit 2. Target must be an absolute path OUTSIDE the calling repo (default is a fresh /tmp/ruflo-mint-<ts>-<name>/ dir).
Refuses existing target. Won't overwrite — must scaffold into a non-existent dir.
Subprocess + 60s timeout. No library import, no in-process execution. The mint stays sandboxed from ruflo's runtime.

Algorithm

Implementation: scripts/mint.mjs.

Validate --name, --template. Default --host to claude-code.
Resolve --target (default: temp dir).
Run safety checks (no project-root writes; target must not exist).
Without --confirm: emit dry-run plan, exit 0.
With --confirm: shell npx metaharness new <name> --template <id> --host <id> --target <abs> --yes.

Templates

minimal, vertical:coding, vertical:devops, vertical:support, vertical:legal, vertical:research, vertical:trading, vertical:health, vertical:education, vertical:sales, vertical:business, vertical:crm, vertical:marketing, vertical:advertising, vertical:ai, vertical:agentics, vertical:ruview, vertical:gaming, vertical:repo-maintainer, vertical:exotic.

Hosts

claude-code, codex, pi-dev, hermes, openclaw, rvm, copilot, opencode, github-actions.

Example dry-run

$ node scripts/mint.mjs --name my-harness --template vertical:coding --host claude-code
# harness-mint (dry-run)

- action: metaharness new
- name: my-harness
- template: vertical:coding
- host: claude-code
- target: /tmp/ruflo-mint-1718560000-my-harness
- confirm: false
- willWrite: false

Re-run with `--confirm` to actually scaffold.

Why dry-run by default

Ruflo's behavioral rules say "executing actions with care" — destructive or repo-touching actions need confirmation. The dry-run output makes the WHAT visible before the WHEN. A human sees target, decides, then adds --confirm if happy.

---name: harness-mintdescription: Scaffold a custom AI agent harness via `metaharness new <name> --template <id> --host <id>`. Defaults to DRY-RUN (no writes) unless --confirm is passed. Refuses to write to the calling repo root or anywhere inside it. Honors ADR-150 architectural constraint + ruflo's "destructive-action confirmation" pattern.--- The one write-capable skill in the plugin. Every other skill is pure-read. This one calls `metaharness new`, which writes a new directory tree. ## Safety (load-bearing) 1. **Dry-run by default.** Without `--confirm`, the script prints what it would do and exits 0 without touching disk. 2. **Refuses project root.** If `--target` resolves to the current working directory OR any path inside it, the script errors out with exit 2. Target must be an absolute path OUTSIDE the calling repo (default is a fresh `/tmp/ruflo-mint-<ts>-<name>/` dir). 3. **Refuses existing target.** Won't overwrite — must scaffold into a non-existent dir. 4. **Subprocess + 60s timeout.** No library import, no in-process execution. The mint stays sandboxed from ruflo's runtime. ## Algorithm Implementation: [`scripts/mint.mjs`](../../scripts/mint.mjs). 1. Validate `--name`, `--template`. Default `--host` to `claude-code`. 2. Resolve `--target` (default: temp dir). 3. Run safety checks (no project-root writes; target must not exist). 4. Without `--confirm`: emit dry-run plan, exit 0. 5. With `--confirm`: shell `npx metaharness new <name> --template <id> --host <id> --target <abs> --yes`. ## Templates `minimal`, `vertical:coding`, `vertical:devops`, `vertical:support`, `vertical:legal`, `vertical:research`, `vertical:trading`, `vertical:health`, `vertical:education`, `vertical:sales`, `vertical:business`, `vertical:crm`, `vertical:marketing`, `vertical:advertising`, `vertical:ai`, `vertical:agentics`, `vertical:ruview`, `vertical:gaming`, `vertical:repo-maintainer`, `vertical:exotic`. ## Hosts `claude-code`, `codex`, `pi-dev`, `hermes`, `openclaw`, `rvm`, `copilot`, `opencode`, `github-actions`. ## Example dry-run ``` $ node scripts/mint.mjs --name my-harness --template vertical:coding --host claude-code # harness-mint (dry-run) - action: metaharness new - name: my-harness - template: vertical:coding - host: claude-code - target: /tmp/ruflo-mint-1718560000-my-harness - confirm: false - willWrite: false Re-run with `--confirm` to actually scaffold. ``` ## Why dry-run by default Ruflo's behavioral rules say "executing actions with care" — destructive or repo-touching actions need confirmation. The dry-run output makes the WHAT visible before the WHEN. A human sees `target`, decides, then adds `--confirm` if happy.

Frequently asked questions