Skill
a11y-pass
Catch the accessibility failures that ship in almost every AI-built UI. Use after building any interactive component.
@archive228Install SkillAgent Orchestration
Skill
/tool-restraint
Don't over-equip an agent with tools/MCP servers. More tools = more ways to fail and a higher cognitive load. Use when wiring tools or an agent underperforms.
Install
$ npx -y skills add Archive228/loopkit --skill tool-restraint --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/tool-restraint
Context preview
The summary Claude sees to decide when to auto-load this skill.
Don't over-equip an agent with tools/MCP servers. More tools = more ways to fail and a higher cognitive load. Use when wiring tools or an agent underperforms.
SKILL.md
tool-restraint.SKILL.mdname: tool-restraint description: Don't over-equip an agent with tools/MCP servers. More tools = more ways to fail and a higher cognitive load. Use when wiring tools or an agent underperforms. when_to_use: adding MCP servers, an agent with many tools, "give it access to everything"
Tool Restraint
Loading an agent with 14 MCP servers "just in case" makes it slower and dumber, not more capable — tool-use agents hit sharp capability cliffs as cognitive load rises.
- Enable **only** the servers the current work actually uses. Remove the rest.
- Prefer official servers for credentialed tools; never install five speculatively.
- Each tool's description eats context on every turn — fewer, sharper tools beat a junk drawer.
- Before adding a write-scoped server, add a hook that logs every call.
If the agent picks the wrong tool or thrashes, the fix is usually fewer tools with clearer descriptions, not a smarter model.
Ships withloopkit
33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI).
Get the whole plugin
Other skills on loopkit.
@archive228Install SkillSkill
active-memory-reminder
Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable). Read it alongside claude-progress.txt…
@archive228Install SkillSkill
adversarial-verify
Review a diff against the goal spec assuming the code is BROKEN. The reviewer
@archive228Install SkillSkill
authz-check
Verify that an endpoint checks ownership, not just authentication. Use on any handler that reads or mutates user data.
@archive228Install SkillSkill
bisect-regression
Find the exact commit that introduced a bug. Use when something worked before and broke, and you don't know which change did it.
@archive228Install SkillSkill
broken-window-check
Before picking new work, smoke-test the last "completed" feature. If it's broken, revert and re-open it before touching anything…
@archive228Install Skill