What does Plan Usage Guard do?

Before long, unattended or multi-agent work, Claude checks your 5-hour session limit and weekly limit and answers GO, GO with checkpoints, WAIT or STOP, with the reset time for each limit. On long jobs it re-checks between phases, and if a limit gets close it finishes the current step, writes a progress note, and gives you one line to send to resume.

Does this work in Cursor, Codex or Copilot?

No. Session and weekly plan limits are a Claude Pro and Max feature that only Claude Code reports. On an API key there are no plan limits to check.

Do I need the plan-usage mod?

For automatic checks, yes. It is free and open source (MIT): claude plugin marketplace add potterdigital/plan-usage-mod, then claude plugin install plan-usage@potterdigital. It also shows your limits on a line above the prompt. Without it, Claude asks you for the numbers from the /usage screen and applies the same rules.

Does checking my limits cost usage?

Barely. The mod answers locally from figures Claude Code already has, with no model call and no network request. Claude checks once per phase, not after every step.

Can I change the thresholds?

Yes. The defaults are STOP at 90% weekly and WAIT at 85% session. Add one line to your CLAUDE.md to use your own, for example: Plan usage guard: stop long work at 80% weekly and wait at 75% session.

Plan Usage Guard for Claude Code

Example session with this skill installed

Before I kick off a big overnight refactor across about 40 files, check whether my plan limits can handle it.

Read your context and instructions
Compiled the plan usage guard

Plan check: GO
- Session (5-hour): 0% used, resets 6:20 PM CT (in 1h 54m)
- Weekly: 1% used, resets Sun 5:00 AM CT

The weekly limit has plenty of room. The session limit resets at 6:20 PM CT, so an overnight run will start on a fresh window from there. The reading is from 4:26 PM CT, so it's current.

Session risk: A 40-file refactor with subagents can use up one 5-hour window. If it does, the run stops partway until the next reset.

Auto-pause: It's off, so nothing will stop the run on its own.

Plan: Split the refactor into batches that each leave the files finished. Re-check usage between batches. If a check shows the session near its limit, finish the current batch, write a progress note in the project, and wait for the reset.

Connects securely to your tools. The creator never sees your data.

About this skill

Long Claude Code jobs fail in the worst place when a plan limit runs out partway through: a refactor half applied, a subagent wave cut off, an overnight run that stopped at 2 AM.

Plan Usage Guard makes Claude check your 5-hour session limit and your weekly limit before it starts long work, then give a clear verdict:

GO when there is room
GO with checkpoints when a limit is high: the job is split into phases that each leave files finished, with a re-check between phases
WAIT when the session limit is nearly spent, with the exact reset time
STOP when the weekly limit is nearly gone or a limit is already hit

When a limit gets close mid-job, Claude finishes the step in progress, writes a progress note, and tells you the one line to send to resume.

How it gets the numbers. Live figures come from the free, open-source plan-usage mod, which reads the limits Claude Code already receives with each reply. No network calls, no model calls, no credentials. Without the mod, the skill asks you for the figures from Claude Code's /usage screen and applies the same rules.

What's inside

SKILL.md: when to check, the decision table, how to stop cleanly, output format
references/tool-output.md: every field the usage tool returns
examples/scenarios.md: six worked cases, from plenty of room to tool not installed

Default thresholds are 90% weekly and 85% session. Set your own with one line in your CLAUDE.md.

How to use

Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

Reviews

No reviews yet

Be one of the first to try it. Every listed skill passes our trust checks below.

Security scanned

Passed our 8-point scan before listing

Fresh listing

Recently published to Agensi

Free forever

No account required to browse

Plan Usage Guard for Claude Code