{"name":"agent-usage-guard","repo":"rbartoli/agent-usage-guard","url":"https://midorreal.com/project/rbartoli-agent-usage-guard","repository":"https://github.com/rbartoli/agent-usage-guard","description":"A Claude Code mod that holds subagent fan-out, heavy-context prompts and retry loops before they spend your usage window. It reads your plan's usage, counts agents across every session, and asks in Claude Code's own dialog.","facts":{"license":{"value":"MIT","source":"https://github.com/rbartoli/agent-usage-guard","checked":"22 Nov 2026"},"language":{"value":"TypeScript","source":"https://github.com/rbartoli/agent-usage-guard","checked":"22 Nov 2026"},"last_release":{"value":"agent-usage-guard--v1.2.1, 10 Nov 2026","source":"https://github.com/rbartoli/agent-usage-guard/releases","checked":"22 Nov 2026"},"releases":{"value":"16","source":"https://github.com/rbartoli/agent-usage-guard/releases","checked":"21 Nov 2026"},"contributors":{"value":"1","source":"https://github.com/rbartoli/agent-usage-guard/graphs/contributors","checked":"21 Nov 2026"},"archived":{"value":"no","source":"https://github.com/rbartoli/agent-usage-guard","checked":"22 Nov 2026"}},"stars":102.0,"writeup":{"what_it_is":"agent-usage-guard is a Claude Code mod that runs inside Claude Code and holds subagent fan-out, heavy-context prompts and retry loops before they spend usage. It reads the plan's live 5-hour and weekly usage percentages and asks the user in Claude Code's own question dialog, or refuses when no one can answer.","audience":"Claude Code users who want to limit agent spend against their plan's usage window","claims":[{"kind":"specific","claim":"Holds agent spawns once the plan window reaches a set percentage","excerpt":"New agents are refused once a window is this full","status":"not_checked"},{"kind":"specific","claim":"Limits agents running at once across every session on the machine to 4 by default","excerpt":"Agents running at once, across every session on this machine","status":"not_checked"},{"kind":"specific","claim":"Stores counts and coarse buckets, never prompt text, tool inputs or model output","excerpt":"It stores counts and coarse buckets, never prompt text, tool inputs or model output.","status":"not_checked"},{"kind":"specific","claim":"Fails open if one of its hooks fails, so a broken guard does not break the session","excerpt":"If one of its hooks fails, the event goes ahead","status":"not_checked"},{"kind":"broad","claim":"Stops runaway usage before it happens","excerpt":"Stops Claude Code from spending your five-hour usage window in ten minutes.","status":"too_broad"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-22"},"why_now":null,"owner_supplied":null,"score":{"verdict":"sleeper","hype":15,"reality":80,"gap":-65,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T07:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-11-10T01:41:40+00:00","text":"Latest release agent-usage-guard--v1.2.1","source":"https://github.com/rbartoli/agent-usage-guard/releases"},{"date":"2026-10-09T01:41:01+00:00","text":"First release","source":"https://github.com/rbartoli/agent-usage-guard/releases"},{"date":"2026-07-28T18:06:57+00:00","text":"Repository created","source":"https://github.com/rbartoli/agent-usage-guard"}],"cite":"agent-usage-guard is a GitHub project at https://github.com/rbartoli/agent-usage-guard written mainly in TypeScript, described there as \"A Claude Code mod that holds subagent fan-out, heavy-context prompts and retry loops before they spend your usage window. It reads your plan's usage, counts agents across every session, and asks in Claude Code's own dialog\".","attribution":"Data from Mid or Real, https://midorreal.com/project/rbartoli-agent-usage-guard, checked 22 November 2026. Attribution with a link is required.","still_real":null}