Agent Skill

Stop That Shit skill

stop-that-shitlennney/stop-that-shitskills/stop-that-shit/SKILL.md

Complete requested work while preventing speculative defenses and scope creep. Use when considering extra hardening, reviewing possible overengineering, resolving repeated verification loops, following explicit task boundaries, or when the user invokes Stop That Shit. Ordinary use of validation, retries, or dependencies alone is not a trigger.

3.0kMIT

always on

63 tokname + description

once used

1,566 tokSKILL.md body

bundled files

11 KB

repo stars

3.0kGitHub

Install the Stop That Shit skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/lennney/stop-that-shit --skill stop-that-shit

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/lennney/stop-that-shit.git /tmp/stop-that-shit
mkdir -p ~/.claude/skills
cp -R /tmp/stop-that-shit/skills/stop-that-shit ~/.claude/skills/stop-that-shit

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

When	What loads	Cost
Every session	Name and description	63 tok
When the agent uses it	The SKILL.md instructions	1,566 tok
Only if opened	1 bundled files (1 KB)	varies

Until it is used, stop-that-shit costs about 22× less than the median MCP server we measured (1,363 tokens on every turn). Installing all 2 skills from lennney/stop-that-shit would load 138 tokens of descriptions. Skills vs MCP study

Checks

Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

Stop That Shit
Follow the Stop Ladder
Resolve uncertainty without inventing work
Keep the deliverable focused
Respect the task mode
Finish

More skills from lennney/stop-that-shit

All skills in this repo

stsslennney/stop-that-shit
Reduce defensive disclaimers, stacked hedging, and self-protective narration when drafting, rewriting, or auditing proposals, articles, case studies, captions, and other reader-facing prose. Use when defensive wording is requested for review or appears in a draft, including wording the assistant adds. Preserve meaningful limits; do not perform general style cleanup or ordinary code work.
3.0k75 tok idle · 858 in use