Usage Guard — AI skill for Claude Code
Guard a running swarm against the claude.ai session usage limit.
How to install Usage Guard
Installs to ~/.claude/skills/jtims-claude-code-swarm-kit-usage-guard/SKILL.md
mkdir -p ~/.claude/skills/jtims-claude-code-swarm-kit-usage-guard && curl -fsSL https://raw.githubusercontent.com/jtims/claude-code-swarm-kit/HEAD/commands/usage-guard.md -o ~/.claude/skills/jtims-claude-code-swarm-kit-usage-guard/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Usage Guard does
description: 'Guard a running swarm against the claude.ai session usage limit. Reads the usage page in the owner''s Chrome on a fixed tick, screenshots every Nth tick, logs to the project, and at the threshold (default 95 percent) runs the capture-then-stop pause. Args: [threshold] [interval_s]' argument-hint: '[threshold=95] [interval_s=150]'
/usage-guard $ARGUMENTS
Owner rulings this encodes (2026-09-04, verbatim): "when I say 'pause', you immediately capture all context via script
Alternatives in AI
- Surface — Show ranked attack surface for a target from its recon manifest + hunt memory 3.8k ★
- TokenTracker — Local-first AI token usage & cost tracker for 31 coding tools incl 1.4k ★
- Room — Open-source earning-focused swarm intelligence engine 838 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
AI Tech Task Solver Chrome Extension
Simple Chrome extension that uses AI (OpenAI GPT-4 Vision, Anthropic Claude) to analyze web page screenshots,
Agent Trading Journal
AI trading journal MCP server: Claude Code, Codex or any MCP agent logs trades from chart screenshots, checks
Browser Copilot
AI side-panel assistant for Chrome. Reads the active page and acts on it with your approval — click, type, swi
Spread Your Claudes
Offload your coding agent's big-context reads to other AI CLIs (Gemini, Cursor, Codex, paid Gemini web app) so
Skill Cost
Multi-harness token-usage cost reporter for AI agent sessions (pi, Claude Code, Codex, opencode). Reads JSONL
Prompt Warrior
Agent skill: your AI coding logs as a gamified character sheet — Claude Code, Codex, OpenCode, Gemini, Copilot
Related Agents
Sf Quality Gate
Runs the local Salesforce quality gate - formatting, ESLint, Code Analyzer, and Jest - then triages every find
Deep Review Guard Bypass
Traces guard functions (permission, capacity, rate-limit, validation) to find any code path that reaches a pro
Search Issues
gh search issues --repo {owner/repo} "llms.txt OR AI-friendly OR LLM documentation OR AI context" --limit 20 g