Skip to content
Back to skills

Kit Rules

ASecurity

The kit's working rules for every reply and task. Load at the start of every session and subagent, before any other tool call.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 12, 2026
ai-agentsgo

Security analysis

A100/100

Pro scans all 8 files and shows the line behind each finding

Scanned November 12, 2026

npx -y skills add ku5ic/claude-kit --skill kit-rules --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Kit Rules?

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

Security grade badge for Kit Rules
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ku5ic-kit-rules/badge)](https://www.skillsdirectory.com/skills/ku5ic-kit-rules)

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: kit-rules
description: The kit's working rules for every reply and task. Load at the start of every session and subagent, before any other tool call.
user-invocable: false
---

# Kit rules

The hard rules, each owned by the section it names:

- The first line of a reply is the answer: `skills/kit-rules/reference/output.md` section 0.
- A fact not read this session gets checked, or goes unsaid: `skills/kit-rules/reference/evidence.md` section 1.
- Never commit or push unasked: `skills/kit-rules/reference/workflow.md` section 1.
- Confirm a destructive, dependency, or config change first: `skills/kit-rules/reference/workflow.md` section 2.
- Temporary files go to `kit scratch-dir`: `skills/kit-rules/reference/output.md` section 3.

Read every file in this table as soon as this skill loads. The rules live in those files, and this one only points at them.

| Before                                                             | Read                                                     |
| ------------------------------------------------------------------ | -------------------------------------------------------- |
| The first edit of a task, or acting on a request with two readings | [reference/workflow.md](reference/workflow.md) section 4 |
| A commit, push, branch, install, delete, or plan                   | [reference/workflow.md](reference/workflow.md)           |
| Writing a file, a report, or a message someone else reads          | [reference/output.md](reference/output.md)               |
| Editing code                                                       | [reference/change.md](reference/change.md)               |
| A claim about code, a version, or a result                         | [reference/evidence.md](reference/evidence.md)           |
| Saying done, fixed, or passes                                      | [reference/verify.md](reference/verify.md)               |
| Spawning an agent                                                  | [reference/subagents.md](reference/subagents.md)         |
| A search, a read over several files, or a scratch path             | [reference/tooling.md](reference/tooling.md)             |

Files in this skill

  • SKILL.md2.1 KB
  • reference/change.md4.5 KB
  • reference/evidence.md1.8 KB
  • reference/output.md4.1 KB
  • reference/subagents.md2.3 KB
  • reference/tooling.md4.5 KB
  • reference/verify.md5.1 KB
  • reference/workflow.md4.4 KB

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.

View all in ai-agents →

Comments

Loading comments…

Newsletter

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