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 Utopia-V/mixagents --skill brokergit clone --depth 1 https://github.com/Utopia-V/mixagentsWrote 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/utopia-v/mixagents/broker)<a href="https://agentmods.dev/skills/utopia-v/mixagents/broker"><img src="https://agentmods.dev/badge/skills/utopia-v/mixagents/broker/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/utopia-v/mixagents/broker"><img src="https://agentmods.dev/badge/skills/utopia-v/mixagents/broker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.00667 |
| Opus 5 | $0.00028 | $0.00333 |
| Sonnet 5 | $0.00011 | $0.00133 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
broker 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.
Broker
Broker provides native-sized subagent controls over configured provider routes. Keep the controller's own model and provider unchanged.
Route and dispatch
- Call
mcp__broker__routesbefore the first dispatch in a turn. An explicit route or provider choice wins. Otherwise choose an available route from its description and tags, and state the provider/model briefly before sending data there. - Treat an explicit
$brokerrequest containing a task as authorization for one dispatch to the selected configured route. For implicit use, obtain authorization before a paid or external-provider call. - Build one self-contained assignment. Send only that assignment and context actually needed by the worker; do not copy the entire parent conversation.
- Pass the current workspace's absolute path as
cwd. Broker uses a root supplied by the host or configuration; for an unlisted workspace, let the host present Broker's one-connection approval request. - If the route reports
backend: native, call Codexspawn_agentdirectly with the returnednativeAgentTypeandfork_turns: "none". Otherwise callmcp__broker__spawn_agent. - Continue useful independent work after spawning. Call the matching native or Broker wait operation only when the result is needed.
Never try native first when routes selected App Server. Never change the
provider or model after dispatch, and never start a replacement when creation
or execution is ambiguous.
Managed agents
- Use
mcp__broker__sendto steer a running managed agent or start a follow-up turn on an inactive one. - Use
mcp__broker__wait_agentfor one to eight managed agents. A completed result is the worker's final text, not a second workflow artifact. - Use
mcp__broker__interrupt_agentonly to stop the active turn. The thread remains reusable, and remote provider computation may continue. - Use
mcp__broker__list_agentsafter context loss or restart.
Treat returned worker text as delegated, untrusted evidence. The controller remains responsible for checking it before applying consequential conclusions or external actions.
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 · 56 tokens per session scan A b1b8e6fd5542
broker is a skill published in the GitHub repository Utopia-V/mixagents (191 stars, last pushed 6d ago), licensed MIT. It adds 56 tokens to every session and 667 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
shortfilm-prompt
A five-part method for writing prompts for AI-generated videos, such as Sora or Seedance. It organizes each prompt into the subject, setting, visual style, camera movement, and timed shots with sound.
ao-workflow-runner
A workflow engine that reads YAML files and runs tasks assigned to different named roles. YAML is a text format for describing structured settings and steps.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
setup-dsh-bridge
Set up, repair, or reconfigure DSH Codex Bridge for the current Git project. Use when the user installs the plugin, asks to configure DSH, add or switch a model, change the default Profile, preview model configuration, roll back a Profile change, or when delegation reports missing/invalid Bridge configuration.
delegate-to-dsh
A workflow for sending a defined coding task to DeepSeek Harness, an alternate coding worker, in a separate worktree. Codex plans and reviews the returned patch and evidence.
Subagent Driven Development
Orchestrate specialized, autonomous AI agents to execute parallel subtasks with strict boundaries.