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 Vanyangyang/cursor-bridge --skill grok-build-supervisorgit 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-build-supervisor)<a href="https://agentmods.dev/skills/vanyangyang/cursor-bridge/grok-build-supervisor"><img src="https://agentmods.dev/badge/skills/vanyangyang/cursor-bridge/grok-build-supervisor/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/vanyangyang/cursor-bridge/grok-build-supervisor"><img src="https://agentmods.dev/badge/skills/vanyangyang/cursor-bridge/grok-build-supervisor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 14 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00103 | $0.03959 |
| Opus 5.5 | $0.00041 | $0.01584 |
| Sonnet 5.5 | $0.00021 | $0.00792 |
| Haiku 4.5 | $0.00010 | $0.00396 |
Grade A, and why
grok-build-supervisor 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grok Build Supervisor
Use the grok-build-supervisor MCP tools as a guarded transport. A user-level daemon owns a separate Leader, ACP connection, visible TUI records, and event journal for each workspace, independently of any one host task. Workspaces share the initialized proxy settings. Each task gets a thin authenticated MCP client. Keep transport diagnostics internal during normal work and report only ready, working, needs permission, needs input, completed, or failed.
User-facing messages
- Render user-facing explanations in this order: an explicit language request, otherwise the language of the user's latest substantive message/current task, otherwise a genuinely known host or OS locale, otherwise English. Never persist an inferred language. Keep JSON keys, states, enum values, tool names, permission/form option values, paths, commands, hashes, task/session/agent IDs, and error/status codes verbatim.
- Keep preflight silent. Tool availability, tool counts or names, Supervisor reachability, ACP/Leader state, the working directory, and presentation details are internal unless they block the request or the user explicitly asks for diagnostics.
- Do not ask the user to create, open, show, resume, or select a TUI as a separate step.
/grok_execute onowns workspace selection and session setup. If startup takes long enough to merit an update, give only a short localized statement that Grok is connecting. - For
/grok_execute on, return one concise standalone result after the visible TUI is ready: executor mode is on, the terminal is ready, and the user can provide the task. The one attention-state exception isneeds_workspace_trust: explain that Grok is waiting for the user's trust decision in the already-open terminal and that/grok_execute onmust not be run again. Render either message using the language rule above. Keep executor mode pending, then inspect the same session again after the user decides. For ordinary task dispatch, report the task state or outcome instead of narrating TUI lifecycle details. - Do not volunteer that no development prompt was sent. Mention that boundary only when the user explicitly asked to open a session without sending work or could otherwise reasonably mistake connection setup for submitting a task.
- For blocked or failed states, report only the actionable cause and next step; expose transport diagnostics only on request.
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.
- 1mo ago Changed · +1 lines a8bf89b7d05f
- 1mo ago Changed 35282983db96
- 1mo ago Changed · +2 lines 0bc8b2ef494c
- 1mo ago Changed · +2 lines 0dafb114b302
- 1mo ago First seen · 84 lines · 103 tokens per session scan A 681542338e3a
grok-build-supervisor is a skill published in the GitHub repository Vanyangyang/cursor-bridge (82 stars, last pushed 10d ago), licensed MIT. It adds 103 tokens to every session and 3,959 once invoked, about $0.0004 per session on Opus 5.5. 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
cp-gate
A checkpoint workflow for confirming requirements, the proposed solution, and the implementation plan. It uses CP1, CP2, and CP3 in a defined order, with the third checkpoint depending on the type of work.
dev-plan-review
A two-stage review process for checking technical plans before and during implementation. The description does not explain what kinds of plans or checks it performs.
dev-testing
A testing guide that defines when to use unit, integration, API, and end-to-end tests. Unit tests check small pieces of code, while end-to-end tests check a full user flow.
routing
A reference guide that maps identified user intentions to the workflows that should handle them. The actual routing is defined by the wider instruction and workflow system.
gauntlet-loop
Beat a real-world quality bar with a Gauntlet Loop: take a GOAL and a REAL-WORLD EQUIVALENT with an inspectable reference pack, decompose into independent parts, assign specialist builders, and gate each part behind a separate fresh-context critic. Pass only if better than the reference; otherwise return the largest…
ai-agent-system-architecture
An architecture guide for AI agent systems, including how agents choose routes, call tools, manage context, remember information, and handle state. It also covers permissions, human involvement, monitoring, replay, and governance.