limite
Stop burning the Claude Code usage limit on easy work. Installs two Haiku sub-agents (Explore for code search and reading, chores for mechanical edits and commands) and a CLAUDE.md note that routes every easy task to them, so Opus keeps only planning, debugging and multi-file changes. Use when the user says "limite", hits their Claude limit too fast, or wants cheap models on easy tasks.
How do I install this agent skill?
npx skills add https://github.com/melvynx/shared-skills --skill limiteIs this agent skill safe to install?
- Gen Agent Trust Hubpass
This skill is safe. It is a configuration utility designed to optimize usage limits in Claude Code by delegating simple tasks (like file searching and minor edits) to a more cost-effective model (Haiku) while keeping the primary model (Opus) for complex reasoning. It involves writing local markdown configuration files to standard agent directories with user consent.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
limite
Claude Code runs every task on the session model. On Opus that includes finding a file, reading a log
or renaming an import, and each of those eats the usage limit. The built-in Explore sub-agent inherits
the session model too, so code search also runs on Opus. This skill moves the easy work to Haiku
(model: haiku, always the latest Haiku), which costs a fraction of Opus per token.
What the user typed after /limite: $ARGUMENTS
Scope
- Default: user scope, every project. Agents go to
~/.claude/agents/, the note to~/.claude/CLAUDE.md. --project(or the user asks for this project only): agents go to.claude/agents/, the note to./CLAUDE.mdat the repo root.
Steps
- Read
templates/Explore.mdandtemplates/chores.mdfrom this skill's folder. - For each one, check the target agents folder (create it if missing):
- Missing: write it.
- Present and identical: skip it.
- Present and different: show the diff and ask before replacing it. Never overwrite silently.
- Read
templates/CLAUDE-note.md. If the targetCLAUDE.mdalready has a## Modelssection (or the same rules in another language), leave it. Otherwise append the section, translated to the language the rest of thatCLAUDE.mdis written in. Create the file if it does not exist. - Tell the user what was written, with the paths, then:
- Restart Claude Code (or open
/agents) so the new agents load. - Check
/agents: Explore and chores must both show Haiku. - The session itself stays on Opus. Only the delegated work moves to Haiku.
- Restart Claude Code (or open
Notes
- A user agent named
Explorereplaces the built-in one, that is the point of the first template. - Haiku is fine for search, reading and one-line edits. Anything that needs judgment stays on Opus: the chores agent stops itself when a task touches more than 2 files or needs a design decision.
- Anthropic does not publish how much each model weighs in a subscription limit, only that Opus uses much more of it than Sonnet, and Sonnet more than Haiku. Do not promise a number.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/melvynx/shared-skills/limite">View limite on skillZs</a>