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 giang6283623/minimal-vibe-coding-kit --skill agent-control-centergit clone --depth 1 https://github.com/giang6283623/minimal-vibe-coding-kitWrote 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/giang6283623/minimal-vibe-coding-kit/agent-control-center)<a href="https://agentmods.dev/skills/giang6283623/minimal-vibe-coding-kit/agent-control-center"><img src="https://agentmods.dev/badge/skills/giang6283623/minimal-vibe-coding-kit/agent-control-center.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 | $0.00105 | $0.01808 |
| Opus 5 | $0.00053 | $0.00904 |
| Sonnet 5 | $0.00021 | $0.00362 |
| Haiku 4.5 | $0.00011 | $0.00181 |
Grade A, and why
agent-control-center 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 7d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Control Center
Coordinate one task without confusing the controller, host, worker, model, or transport. Keep exactly one controller responsible for the plan, dispatch decisions, verification, and final acceptance.
Core invariants
- Treat the active application or CLI as the host. The host exposes tools and retains execution authority even when another provider is the controller.
- Treat a model as a capability behind a host, not as a controllable process.
- Keep the host parent as the user-facing relay and execution authority. An external controller owns orchestration decisions, but cannot widen host permissions or directly control native agents.
- Keep controller and worker provider, transport, model, and reasoning choices separate. Selecting a controller never assigns that provider as a worker.
- When an external controller is active, topology skills run in executor mode: the controller creates work orders and reviews receipts, while the host asks user questions, dispatches approved workers, and returns their receipts.
- Never claim that plain MCP lets a server click, control, or spawn agents in its client. Use host-mediated work orders and proof receipts.
- Give every worker a bounded scope, budget, expected artifact, validation, and stop condition. Do not permit recursive worker dispatch unless the work order explicitly allows one bounded child layer.
- Allow at most one controller transfer per task. Require user approval before a transfer changes provider, billing, permissions, or mutation authority.
- Preserve repository rules, protected paths, human gates, and user-owned changes across every provider boundary.
Inputs
Resolve these values before dispatch:
objective: one observable outcome;controller:native,auto, or a registered provider identifier such ascodex,claude,cursor,opencode,grok, orkimi; default tonativeunless the user requests cross-provider control or automatic selection;relay_mode:automatic-host-relayorsequential-host-relayfor a non-manual controller transport; bindmanual-handoffautomatically whencontroller_route.transport=manual;controller_route: controller provider, transport, model, and supported reasoning effort;worker_routes: default or per-role worker provider, transport, model, and supported reasoning effort, selected independently from the controller;topology:plan-only,sequential,countercheck,parallel-analysis,verified-graph, orproofline;scope: repository root, allowed paths, protected paths, and external systems in scope;authorization: read-only or approved mutation boundaries;budget: lane count, time, retries, and any user-stated cost limit;acceptance: commands, artifacts, objective checks, and human gates.
What ships with it
11 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.
- agents/openai.yaml 274 B
- examples/cursor-codex-cursor-workers.json 4.2 KB
- examples/native-sequential.json 2.2 KB
- references/capability-contract.md 5.2 KB
- references/codex-cli-bridge.md 7.9 KB
- references/controller-modes.md 5.2 KB
- references/handoff-contract.md 7.4 KB
- references/provider-selection.md 8.8 KB
- schemas/controller-response.schema.json 3.8 KB
- scripts/codex-cli-controller-bridge.mjs 82 KB runs code
- scripts/validate-controller-contract.mjs 23 KB runs code
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.
- 7d ago First seen · 153 lines · 105 tokens per session scan A 9cf9e064d055
agent-control-center is a skill published in the GitHub repository giang6283623/minimal-vibe-coding-kit (21 stars, last pushed 10d ago), licensed MIT. It adds 105 tokens to every session and 1,808 once invoked, about $0.0005 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
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…