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 agentmods add skills/vanyangyang/cursor-bridge/grok-executor-modenpx skills add Vanyangyang/cursor-bridge --skill grok-executor-modegit clone --depth 1 https://github.com/Vanyangyang/cursor-bridgeWrote 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/vanyangyang/cursor-bridge/grok-executor-mode)<a href="https://agentmods.dev/skills/vanyangyang/cursor-bridge/grok-executor-mode"><img src="https://agentmods.dev/badge/skills/vanyangyang/cursor-bridge/grok-executor-mode.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.01409 |
| Opus 5 | $0.00036 | $0.00705 |
| Sonnet 5 | $0.00015 | $0.00282 |
| Haiku 4.5 | $0.00007 | $0.00141 |
Grade A, and why
grok-executor-mode 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grok Executor Mode
Use $grok-build-supervisor as the required transport and lifecycle contract. This skill changes role allocation for the current host task; it does not replace the Supervisor or claim to be a native host collaboration mode.
Activation and lifetime
- Only an exact, case-insensitive
/grok_execute onmay activate the mode for the current host task. First bind the current host task's absolute project directory, inspect Supervisor status, and immediately reuse or open its guarded session with the default visible Windows Terminal TUI. If Grok returns exact workspace-trust state, keep activation pending, preserve the same TUI, and tell the user to decide in that terminal without rerunningon; never simulate the answer or pass--trust. Commit activation only after that session is verified ready; a failed setup leaves the mode off. Opening the TUI is authorized byon, but sending a development prompt is not. Reply with one short ready confirmation in the language of the user's latest substantive message unless the user explicitly requests another language. Do not persist an inferred language. - The most recent exact
/grok_execute onor/grok_execute offinstruction in this task controls the mode. The selected workspace and activation remain task-local untiloffor the task ends; never write either to global proxy configuration and never silently switch directories while active. - While active, automatically apply this role contract to every subsequent ordinary user task that requires execution. The user does not repeat a slash command or Skill name for each task.
- Do not ask the user to create, resume, select, or manage a TUI, session ID, process, Leader, or ACP connection. The
onflow owns that setup. A visible TUI remains the default unless the user explicitly requested headless operation before activation. - Only an exact, case-insensitive
/grok_execute offdeactivates the mode and clears the task-local workspace binding. It does not automatically cancel a running prompt, disconnect ACP, close the visible TUI, or stop the owned Leader; continue any already-required Supervisor monitoring under the normal transport contract and report that work separately. /grok_executewith no argument or any argument other than the exact control words changes nothing and returns only the two valid forms.- Direct
$grok-executor-modeinvocation may explain or apply the policy only when a prior/grok_execute onis active. It never changes mode state itself. - Do not infer activation or deactivation from any other wording, including ordinary requests that merely mention Grok.
What ships with it
1 file 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.
- 5d ago First seen · 60 lines · 73 tokens per session scan A a16e7bdc389d
grok-executor-mode is a skill published in the GitHub repository Vanyangyang/cursor-bridge (71 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 1,409 once invoked, about $0.0004 per session on Opus 5. 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 2026-08-30.
Other skills, from other repositories
self-audit
작업을 "완료"라고 보고하기 직전, 스스로 결과를 감사할 때. 커밋/PR 직전 최종 점검에도 사용.
grok-runtime
Internal helper contract for calling the grok-companion runtime from Claude Code or Codex. Reference when invoking the Grok companion script or the groksearch MCP tool.
cp-gate
执行 CP1(需求确认)/ CP2(方案确认)与条件 CP3(实施计划确认)。CP1→CP2 强制按序,CP3 按工作流能力矩阵判定。.
spec-governance
规范治理生命周期 — 意图驱动记录、RecordRouter 分流、SCV 规范变更验证;规范吸纳执行细节由 spec-absorption 承接.
dev-plan-review
技术方案验证(两阶段质量门禁)— PR-1 CP2 前自检 + PR-2~PR-7 详细验证,阻断不合格方案进入编码.
dev-testing
测试规范 — 单元测试/集成测试/API测试/E2E测试四类覆盖标准与触发条件.