Using Mint
Pre-modification gate for projects using the mint development framework. Ensures the mint skill is invoked before any file write, edit, or delete — routing tasks to the correct execution mode with quality gates enforced. Use when a .mint/ directory is present in a project, when starting any coding task, or when about to modify files in a mint-managed repository.
Install
$ agentstack add skill-3li7alaki-mint-using-mint ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-3li7alaki-mint-using-mint) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
For ANY task that writes, edits, or deletes files — invoke mint FIRST. You CANNOT use Write, Edit, or Bash (for file ops) tools until mint is invoked.
Using mint
The Rule
Invoke mint BEFORE modifying any file. mint auto-routes to the right mode based on task complexity. You do not decide the workflow — mint does.
How to Invoke
Use the Skill tool to invoke mint with the user's task description:
Skill({ skill: "mint", args: "Add dark mode toggle to the settings page" })mint will auto-detect the right mode, announce the routing decision, and execute with quality gates and disciplined delegation.
When mint Applies
| Task | Mode | |------|------| | Feature implementation | plan or ship | | Bug fix | quick or plan | | Refactor | plan | | Config change (≤3 files) | quick | | Research / investigation | research | | Check quality gates | verify | | Pure conversation / reading files | No — mint not needed |
If you're tempted to skip mint ("this is just a small fix", "I'll edit one file directly") — that's exactly when mint matters most. Small fixes use quick mode. mint enforces gates even on single files.
What mint Provides
- Auto-routing — quick/plan/research/ship/verify based on complexity
- Quality gates — lint + types + tests enforced before every commit
- Multi-stage review — spec review, then parallel audit (quality, security, conventions, tests, business)
- Learning loop — past failures become future prevention via issues.md
- Context protection — main context stays clean, heavy work delegated to subagents
Configuration
mint expects .mint/config.json in the project root. If it doesn't exist, mint will prompt to run init.
Override
The user can always override mint's routing:
- "No, just quick-fix it" → switches to quick mode
- "Actually plan this out" → switches to plan mode
- "Skip mint, just do X" → respect the override, but warn about skipped gates
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: 3li7alaki
- Source: 3li7alaki/mint
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.