Skip to content
Back to skills

Gates

ASecurity

What each gate level (strict, standard, light) switches on and off, and what never relaxes at any level. Use when setup asks the founder to choose a level, when the level changes, and whenever an agent is unsure whether a step is required.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 14, 2026
ai-agentsgosecurity

Works with

  • cli

Security analysis

A100/100

Scanned October 14, 2026

npx -y skills add Fadi88/one-man-startup --skill gates --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Gates?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Gates
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fadi88-gates-one-man-startup/badge)](https://www.skillsdirectory.com/skills/fadi88-gates-one-man-startup)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: gates
description: What each gate level (strict, standard, light) switches on and off, and what never relaxes at any level. Use when setup asks the founder to choose a level, when the level changes, and whenever an agent is unsure whether a step is required.
---

# Gate levels

`project.toml [gates] level` is one of three values. Explain them to the founder in these
words, not in your own; a level is what this file says it is.

## Never relaxed, at any level

- Outward steps (deploy, merge, push, publish, send, pay, delete, real data writes) wait for the
  founder's go, one step at a time (`skills/ordered-steps/`).
- Data writes prove themselves and can be undone (`skills/safe-data-write/`).
- The commit-msg hook: the founder is the only author, no tool credited, banned characters
  refused (`skills/commit/`).
- No unconfirmed assumptions (rule 11), and every rejected idea is recorded (rule 13).
- Free tiers are strict, with tested caps before release.

## What changes

| | strict | standard | light |
|---|---|---|---|
| Requirement row before a change | always, new or cited | always for features; a copy or style fix may skip it, noted in `docs/HISTORY.md` | optional |
| Grilling and readiness gate | every feature | every feature | none |
| Spec audit (`skills/spec-audit/`) | every feature | features touching existing code | none |
| Security and legal review | every feature touching data, money, AI output or claims | only where the feature's spec flags them | before any real user or real data |
| Full sweep | before every hand-off and every commit | before every commit | before every commit |
| QA report | every change | every feature | before any real user |

**Light is for throwaway prototypes only:** no real users, no real personal data, no payments.
Moving from light to anything else means writing the missing requirement rows first.

## Recommending

Setup always recommends strict and says what it buys, using the table above. If the founder
chooses another level, record the level, the reason and when to revisit it in
`p1-closed-decisions.md`, and the declined recommendation in `p1-rejected.md`.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.