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.
git clone --depth 1 https://github.com/Horosheff/cursor-jrWrote 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/commands/horosheff/cursor-jr/cursor-jr-maintain)<a href="https://agentmods.dev/commands/horosheff/cursor-jr/cursor-jr-maintain"><img src="https://agentmods.dev/badge/commands/horosheff/cursor-jr/cursor-jr-maintain/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/horosheff/cursor-jr/cursor-jr-maintain"><img src="https://agentmods.dev/badge/commands/horosheff/cursor-jr/cursor-jr-maintain.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00114 |
| Opus 5.5 | $0.00000 | $0.00046 |
| Sonnet 5.5 | $0.00000 | $0.00023 |
| Haiku 4.5 | $0.00000 | $0.00011 |
Grade A, and why
cursor-jr-maintain scanned grade A with 0 findings 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- t-800-maintain — 89% identical, 6 lines differ
What it actually says
CursorJr Maintainer
Вызови maintainer-субагента:
Task(cursor-jr-maintainer)
Передай задачу:
- проверить
knowledge-base/UPDATE-QUEUE.md; - обновить недостающие карточки;
- запустить
scripts/audit-coverage.ps1; - обновить
CHANGELOG.md; - выполнить
scripts/install-plugin.ps1иscripts/verify-install.ps1.
Не используй этот сценарий для ответов новичкам. Для этого есть Task(cursor-jr).
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.
- 1mo ago First seen · 18 lines · 0 tokens per session scan A 848d44d6372c
cursor-jr-maintain is a command published in the GitHub repository Horosheff/cursor-jr (11 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 114 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
refactor
Systematic refactoring: analyze → split → extract → verify behavior, with no truncation or omitted lines.
codemod-safety
Audit a codemod or bulk mechanical transform for behavior-preservation — report only.
integrity-plan
Data-integrity & destructive-op audit — plan only, no migrations or tokens until approved.
auth-flows
Read-only audit of app-layer auth — route×gate matrix, getSession vs getUser, middleware-as-only-gate.
rls-plan
Supabase RLS + access-control audit + remediation plan — no SQL until approved.
next-task
Intelligently determine and prepare the next action based on comprehensive context.