easy-vs-right-check

A two-way honesty checkpoint.

Skill by kas1987

IndexedApache-2.0★ 1

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/kas1987-easy-vs-right-check

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

A two-way honesty checkpoint. Before a step that feels like progress, ask whether you are taking it because it is right or because it is easy. The mirror — before holding or stopping, ask whether autonomous work still remains. Use at both edges: starting a step that only looks like progress, and stopping too early.

Reviews

Write a review

No 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

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/easy-vs-right-check

What's inside

Skill name: easy-vs-right-check
Description: A two-way honesty checkpoint. Before a step that feels like progress, ask whether you are taking it because it is right or because it is easy. The mirror — before holding or stopping, ask whether autonomous work still remains. Use at both edges: starting a step that only looks like progress, and stopping too early.
License: Apache-2.0
Instructions: 22 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

# Easy vs Right Check

## Forward — am I dodging the work?

Before a step that looks like progress:

- Am I taking this because it is right, or because it is easy?
- Does it pass a check I designed on a simplified model while the real integration is labeled "later"?
- Am I reaching for the familiar tool over the better one?
- A "this part is unnecessary" dismissal is the most dangerous form — decompose the thing and verify each part before discarding it.

Ask plainly: what would actually fail here, and am I building toward that or around it?

## Mirror — am I stopping too early?

Before "I'll hold here" or "waiting for input":

- Is there autonomous work left? Investigating, building a local proof, verifying, writing up — these are the work.
- Stop only at a genuine external gate: a publish, a send, a payment, a credential, an account action.
- "Holding for the operator" while autonomous work remains is the rule turned backward to justify stopping.

From kas1987/fable-agent-orchestration, Apache-2.0.

Signals

Stars: 1
Forks: 0
Open issues: 0
Last commit (this folder): Aug 13, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: Apache-2.0
Repository: github.com/kas1987/fable-agent-orchestration
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql