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.
npx skills add eaglesakura/agent-skills --skill claude-alias-cursorgit clone --depth 1 https://github.com/eaglesakura/agent-skillsWrote 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/skills/eaglesakura/agent-skills/claude-alias-cursor)<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/claude-alias-cursor"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/claude-alias-cursor/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/skills/eaglesakura/agent-skills/claude-alias-cursor"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/claude-alias-cursor.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 | $0.00232 | $0.03743 |
| Opus 5 | $0.00116 | $0.01871 |
| Sonnet 5 | $0.00046 | $0.00749 |
| Haiku 4.5 | $0.00023 | $0.00374 |
Grade C, and why
claude-alias-cursor scanned grade C with 2 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 9d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
1. `agent` または `cursor agent` が使えること（未導入なら `curl https://cursor.com/install -fsS | bash`） Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. `agent` または `cursor agent` が使えること（未導入なら `curl https://cursor.com/install -fsS | bash`） How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude → Cursor Agent CLI エイリアス
この環境では Claude Code（claude）は未契約である。他 SKILL や手順が claude を提案しても、実行せず Cursor CLI の Agent CLI に置き換える。
最優先（skill-creator / description 最適化）
transcript で起きやすい失敗: skill-creator が run_loop を指示 → claude が無いと気づく → 手動最適化やスキップに落ちる。これは誤り。
| skill-creator が言うこと | この環境でやること |
|---|---|
python -m scripts.run_loop … |
実行しない（内部が claude -p。FileNotFoundError） |
run_eval / improve_description |
同上。claude -p 依存 |
| description 最適化を進める | 本 SKILL の scripts/trigger_opt_cursor.py を使う |
| 「claude CLI が無いので手動で」 | 禁止。代替スクリプトがある |
# skill-creator の run_loop 相当（Cursor Agent CLI）
python path/to/claude-alias-cursor/scripts/trigger_opt_cursor.py \
--eval-set /path/to/trigger-eval.json \
--skill-path /path/to/target-skill \
--results-out /path/to/results.json \
--max-iterations 5 \
--verbose
# 最良 description を SKILL.md に書き戻すなら --apply-best
- エントリポイント: 環境変数
CURSOR_AGENT_BIN（既定cursor→cursor agent …、agentなら直呼び） - eval set:
[{"query":"…","should_trigger":true}, …] - コマンド置換だけでは足りないことがある（Claude の stream-json Skill 発火検知は Cursor と非互換）。TRIGGER/SKIP 分類が本スクリプトの近似プロトコルである
いつ使うか
- skill-creator の description 最適化・
run_loop/run_eval/improve_descriptionが出たとき（最優先） - 他 SKILL / スクリプト / ドキュメントが
claudeやclaude -pを指示したとき - headless / CI / eval で Claude Code 相当の呼び出しが必要なとき
- ユーザーが「claude の代わりに cursor / cursor-cli / agent」と明示したとき
claude: command not found/ Authentication 以前に CLI 自体が無いとき
いつ使わないか
- IDE 起動だけの
cursor（agentサブコマンドなし）を代替にしようとする誤解を正す以外の、純粋な IDE 操作 - Claude 契約済みで、ユーザーが本物の
claudeを使うと明示しているとき - Cursor SDK の実装だけが対象で、CLI 置換が不要なとき
エントリポイント
次の どちらも Agent CLI である（同等に使ってよい）。
| 呼び方 | 例 |
|---|---|
agent … |
agent -p "…" |
cursor agent … |
cursor agent -p "…" |
IDE を開くだけの cursor（サブコマンドなし）は Agent CLI ではない。置き換え先にしない。
前提
agentまたはcursor agentが使えること（未導入ならcurl https://cursor.com/install -fsS | bash）- 認証済みであること
- 対話:
agent loginまたはcursor agent login（ブラウザ認証） - スクリプト / CI:
CURSOR_API_KEY
- 対話:
- headless（
-p）ではワークスペース信頼が必要なことがある →--trustおよび／または-f/--force - 詳細対応表が必要なら references/command-bindings.md を読む
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 196 lines · 232 tokens per session scan C 918814a97757
claude-alias-cursor is a skill published in the GitHub repository eaglesakura/agent-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 232 tokens to every session and 3,743 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…