Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/eltonylfgi-blip/claude-code-usage-guard/setupnpx skills add eltonylfgi-blip/claude-code-usage-guard --skill setupgit clone --depth 1 https://github.com/eltonylfgi-blip/claude-code-usage-guardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/eltonylfgi-blip/claude-code-usage-guard/setup)<a href="https://agentmods.dev/skills/eltonylfgi-blip/claude-code-usage-guard/setup"><img src="https://agentmods.dev/badge/skills/eltonylfgi-blip/claude-code-usage-guard/setup.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00110 | $0.00849 |
| Opus 5 | $0.00055 | $0.00425 |
| Sonnet 5 | $0.00022 | $0.00170 |
| Haiku 4.5 | $0.00011 | $0.00085 |
Grade B, and why
setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
2. **Open the user's settings.** Path: `~/.claude/settings.json` (Windows: `%USERPROFILE%\.claude\settings.json`). If it does not exist, create it as `{}`. **Always back it up first** (copy to `settings.json.bak`) before How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
usage-guard setup
Most people install usage-guard but never wire the one-time status-line shim, so the real plan quota never turns on and the guard stays silent. This skill does that wiring for them with as little friction as possible. Prefer doing the edit for the user (with a backup) over just printing instructions — the whole point is to remove the manual step.
Steps
-
Locate the installed status-line shim. It lives under the user's Claude plugins dir. Run this (works on macOS, Linux and Windows):
node -e "const fs=require('fs'),p=require('path'),os=require('os');const root=p.join(os.homedir(),'.claude','plugins');let hit;(function w(d){let es;try{es=fs.readdirSync(d,{withFileTypes:true})}catch(e){return}for(const x of es){if(x.name==='node_modules'||x.name==='.git')continue;const f=p.join(d,x.name);if(x.isDirectory())w(f);else if(x.name==='usage-guard-statusline.mjs')hit=f}})(root);console.log(hit||'NOT_FOUND')"If it prints
NOT_FOUND, tell the user to run/plugin install usage-guard@cc-guardfirst, then retry. -
Open the user's settings. Path:
~/.claude/settings.json(Windows:%USERPROFILE%\.claude\settings.json). If it does not exist, create it as{}. Always back it up first (copy tosettings.json.bak) before editing. -
Wire the
statusLine, preserving any existing one:- If there is NO existing
statusLine, set it to run the shim directly:"statusLine": { "type": "command", "command": "node \"<ABSOLUTE_PATH_FROM_STEP_1>\"" } - If a
statusLine.commandalready exists, do NOT clobber it — chain it through the env var so their line still renders after the snapshot:
(On Windows the env var is set in the wrapping shell — see TUTORIAL.md for the"statusLine": { "type": "command", "command": "USAGE_GUARD_STATUSLINE='<their existing command>' node \"<ABSOLUTE_PATH_FROM_STEP_1>\"" }.cmdwrapper.)
- If there is NO existing
-
Confirm in one line. Tell the user it's wired, and that after their next couple of Claude Code messages,
/usage-guard:usagewill start with a realReal plan quotablock. Note that real quota only appears on Claude.ai Pro/Max sessions and only after the first API response; until then the weighted fallback is used.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 40 lines · 110 tokens per session scan B 2908c39be68f
setup is a skill published in the GitHub repository eltonylfgi-blip/claude-code-usage-guard (3 stars, last pushed today), licensed MIT. It adds 110 tokens to every session and 849 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
better-auth
Skill for integrating Better Auth - comprehensive TypeScript authentication framework for Cloudflare D1, Next.js, Nuxt, and 15+ frameworks. Use when adding auth, encountering D1 adapter errors, or implementing OAuth/2FA/RBAC features.
aceternity-ui
100+ animated React components (Aceternity UI) for Next.js with Tailwind. Use for hero sections, parallax, 3D effects, or encountering animation, shadcn CLI integration errors.
cloudflare-cron-triggers
Cloudflare Cron Triggers for scheduled Workers execution. Use for periodic tasks, scheduled jobs, or encountering handler not found, invalid cron expression, timezone errors.
cloudflare-durable-objects
Cloudflare Durable Objects for stateful coordination and real-time apps. Use for chat, multiplayer games, WebSocket hibernation, or encountering class export, migration, alarm errors.
cloudflare-sandbox
Cloudflare Sandboxes SDK for secure code execution in Linux containers at edge. Use for untrusted code, Python/Node.js scripts, AI code interpreters, git operations.
cloudflare-browser-rendering
Cloudflare Browser Rendering with Puppeteer/Playwright. Use for screenshots, PDFs, web scraping, or encountering rendering errors, timeout issues, memory exceeded.