Show HN: agent-usage-guard – a Claude Code mod to protect your usage window

Stops Claude Code from spending your five-hour usage window in ten minutes.

agent-usage-guard is a Claude Code mod: it runs inside Claude Code and holds runaway spend before it happens. It reads your plan's live usage, and it holds subagent fan-out, heavy-context churn and retry loops.

Recorded from Claude Code's interactive UI with the guard loaded. A scripted local API stands in for Claude, so the sessions and token counts are staged and no usage is spent. Every question on screen is the guard's own. Rebuild it from the Northstar fixture.

It acts before the spend, not after it: before an agent starts, a prompt is sent, or a tool call runs. Agent limits hold across every Claude Code session on your machine, and fan-out and heavy context are capped at any usage level, not only near the limit. When you are at the keyboard it asks you, in Claude Code's own question dialog. When nobody can answer, it refuses and tells Claude why, so the model can wait, batch the work, or stop. /agent-guard report shows what it did.

Run these commands inside Claude Code v2.1.287 or later:

/plugin marketplace add rbartoli/agent-usage-guard /plugin install agent-usage-guard@agent-usage-guard /reload-plugins

Then run /agent-guard to see what it sees. Mods are on by default; the overview lists the settings that turn them off.

One afternoon I gave Claude Code a research prompt at max effort. It spawned 394 subagent calls, 341 of them running at once, and pushed 84M context tokens through the API in ten minutes. Session over: "Claude usage limit reached." Locked out until the window reset.

That wasn't a one-off. Sixty days of my own logs held 12 lockouts and 166 ten-minute windows with agent bursts. The failure mode multiplies: a large context × rapid tool loops × parallel agents × blind retries. Each protection below removes one factor.

And it's not just me: 339 subagents from a single prompt, half a weekly Max plan consumed by recursive spawning, and multi-agent runs using ~15× the tokens of a chat session.

Area Rule Default What happens

Plan windows New agents need approval once a window is this full 80% asks; approval lasts until that window resets

New agents are refused once a window is this full 95% refuses

New agents need approval when the 5-hour window rises this fast 20 points / 10 min asks

Agents Agents running at once, across every session on this machine 4 asks

Agents started or resumed per 10 minutes, across this machine 12 asks

Tokens processed by subagents per 10 minutes, across this machine 10M asks

Subagents may not start their own agents depth 1 refuses

Context Claude is told once to keep the turn bounded 300k tokens adds a note to the prompt

A prompt that would re-read this much context 500k tokens asks: compact then send, send anyway, or cancel

Tool calls per 10 minutes while a conversation or agent carries this much 20 calls at 400k asks: keep going, compact after this turn, or stop

A heavy session idle long enough for its prompt cache to expire 150k tokens, 1 h idle asks before re-writing the cache

Loops The same tool call failing again and again, with no other call in between 3 identical failures refuses the identical retry

Refused agent calls within 10 minutes 5 pauses agent spawns for 10 min

Agents covers subagents, agent-team teammates, workflow agents, and finished subagents resumed with SendMessage. Each tool call is judged on the context of the loop that makes it, so a small subagent never inherits the main conversation's size.

When it asks. The question appears in Claude Code's own dialog, the one Claude uses to ask you something, and the call waits for your answer. Agents started in parallel while it is open are held back, and Claude starts them again once you answer. If you allow it, that condition stays allowed for a while: a plan window until it resets, a heavy context until it shrinks (for tool calls, an hour at most), the agent counts for 10 minutes. If you decline or dismiss the question, Claude is told not to start agents for the next 10 minutes (AGENT_GUARD_WINDOW_SECONDS), and is not asked again in that time. Typed words reach Claude, so you can answer "use haiku agents instead".

When nobody can answer. In claude -p, the Agent SDK and dontAsk mode, an agent or tool gate refuses instead of asking. A heavy prompt is held with the reason, and so is a dormant heavy resume once the machine-wide cap of one per 10 minutes is reached. Claude reads each refusal as the tool's result. Repeat refusals of the same condition are worded differently each time and escalate: the second says nothing has changed and to try something else, the third says to end the turn. If a Stop hook such as /goal keeps reopening the turn, the refusal says the user has to decide.

What it leaves alone. It never holds a background task's notification or another session's message, because that would lose the result. It no longer blocks prompts after a usage limit: since v2.1.234, Claude Code waits at a limit and continues at reset on its own (autoContinueAtUsageLimit). The guard's job is to keep you from reaching the limit, and its journal counts the lockouts it did not prevent.

/agent-guard [status] what the guard sees right now /agent-guard allow [agents|context] [minutes] lift its limits for this session (default: all, 10 min) /agent-guard pause [minutes] the same as allow, for every limit /agent-guard resume end an allow early, lift the agent pause, and let declined questions ask again /agent-guard report [days] what it did on this machine (default: 7 days) /agent-guard help these commands

/agent-guard runs at once, even mid-turn, and never starts a model turn, so Claude never sees an override and cannot take one as permission. Sending [allow-usage-guard] or [allow-agent-burst] alone as a prompt, the markers of earlier versions, does the same as /agent-guard allow or allow agents.

Mods run in claude in a terminal, in the Desktop app's Code tab, in claude -p and the Agent SDK. They don't run in a Desktop-app WSL session (where mods run).

Native limits still matter. Claude Code caps a session at 20 concurrent subagents (CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS) and three layers of nesting (CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH). It has no limit on the total number of agents a session starts. The guard's defaults are stricter and span sessions; the native caps remain the outer wall for the paths the guard only counts.

/agent-guard report 30

The report counts usage-limit lockouts (each locked window once), plan-window threshold crossings, and every question and refusal by rule, with what you answered. It reads every session's journal on this machine and never leaves it. Set AGENT_GUARD_JOURNAL=0 to stop recording.

A mod runs inside Claude Code with your permissions; read what a mod can reach before you install one. This one is about 2,400 lines of TypeScript with no dependencies, and claude plugin validate . lists every API it calls and every environment variable it reads:

Set AGENT_GUARD=0 to turn it off without uninstalling it.

Set these as environment variables, or under env in ~/.claude/settings.json. Times are in seconds; a value that isn't a number in range keeps its default, and /agent-guard says so.

The dormant default assumes the one-hour prompt cache that subscriptions get within plan usage. With an API key or extra usage, the cache lasts five minutes, so set AGENT_GUARD_DORMANT_SECONDS=300.

The rules live in a harness-agnostic core (core/) that performs no I/O. The Claude Code mod is its first adapter. docs/architecture.md describes the contract an adapter keeps and what another agent harness must offer to carry each rule.

claude plugin validate . --strict claude plugin test

claude plugin test runs the suite inside Claude Code's own test kit: unit tests of the core, and tests that fire real Claude Code events through the hooks module with no session, model or network. TESTING.md covers the layers and what each test proves.