Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
agent-usage-guard
A Claude Code mod that reads the plan's live 5-hour and weekly percentages and holds subagent fan-out, heavy-context prompts and retry loops before they burn the window.
v1.1.2 released 2026-10-25; Show HN 2026-10-22 (28 points). (checked 2026-10-25)
In Coding agent usage trackers
Where it stands apart
- Which shared standard or format does it mainly build on? Claude Code's status line and plugin hook interface (10% of 21 others)
- Where do you mainly see it? inside the agent (status line, hook, plugin, mod, or skill) (14% of 21 others)
- Does it only report, or does it change what the agent does? steers or stops the agent (tells it its limits, holds or blocks work near a limit) (5% of 21 others)
What it shares with most of the community
- Is it actively maintained? active (81% of 21 others)
- How is the main thing licensed? permissive open source (MIT/Apache/BSD) (62% of 21 others)
- Can it run entirely on your own device or infrastructure, without the maker's servers? yes (86% of 21 others)
- Do you need an account to use it? no account (71% of 21 others)
- Who is it for? developers (100% of 21 others)
- Does your usage data leave your machine? no; the only outside calls are to the AI provider itself or a public price list (71% of 21 others)
- What access to your provider accounts does it take? none; it reads local files or data the agent hands it (63% of 19 others)
- Whose usage is it built around? one developer's own usage (76% of 21 others)
Nearest neighbors
- Fuel Gauge 100% of 15 shared answers match
- ClaudeStatsBar 79% of 14 shared answers match
- tare 73% of 15 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | active | source 2026-10-26 |
| How is the main thing licensed? | permissive open source (MIT/Apache/BSD) | source 2026-10-26 |
| How is it mainly sustained? | individual side project, no revenue | source 2026-10-26 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | yes | source 2026-10-26 |
| Do you need an account to use it? | no account | source 2026-10-26 |
| Who is it for? | developers | source 2026-10-26 |
| Which shared standard or format does it mainly build on? | stands apart Claude Code's status line and plugin hook interface Claude Code mod/plugin hooks reading the percentages Claude Code reports. | source 2026-10-26 |
| What does it mainly measure? | plan-limit use (% of the 5-hour, weekly, or monthly window and reset times) Plan windows plus agent counts and context size, used to gate work. | source 2026-10-26 |
| Where do you mainly see it? | stands apart inside the agent (status line, hook, plugin, mod, or skill) | source 2026-10-26 |
| Which coding agents does it cover? | Claude Code only | source 2026-10-26 |
| Does it only report, or does it change what the agent does? | stands apart steers or stops the agent (tells it its limits, holds or blocks work near a limit) | source 2026-10-26 |
| Does your usage data leave your machine? | no; the only outside calls are to the AI provider itself or a public price list | source 2026-10-26 |
| What access to your provider accounts does it take? | none; it reads local files or data the agent hands it | source 2026-10-26 |
| Whose usage is it built around? | one developer's own usage | source 2026-10-26 |
| What is the main way to install it? | a package runner or registry (npx, pip/uv, Homebrew formula, agent plugin marketplace) Claude Code /plugin marketplace. | source 2026-10-26 |
Sources
This page was derived from:
- GitHub · github.com/rbartoli/agent-usage-guard · read 2026-10-25
RSS for this project · Its own release feed
Are you a maintainer? Claiming and correcting projects is coming soon.