orchestrator-voice

orchestrator-voice is a skill for Claude Code, Codex from dentiny/kon. It costs 45 tokens per session (608 once invoked), scanned A, original, MIT.

A set of rules for how an orchestrator conducts conversations during `/kon` commands, including when to ask users questions and how to phrase replies.

In plain words
What is it for?
It guides conversational wording, response length, and the use of question widgets during orchestrated coding-agent sessions.
Why use it?
It keeps dialogue focused and prevents premature or repeated questions when the user’s direction is still unclear.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the AskUserQuestion tool.

Good fit It guides conversational wording, response length, and the use of question widgets during orchestrated coding-agent sessions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dentiny/kon/orchestrator-voice
View source ↗ dentiny/kon
Install

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.

Any agent
npx skills add dentiny/kon --skill orchestrator-voice
Clone the repo
git clone --depth 1 https://github.com/dentiny/kon

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for orchestrator-voice

README.md
[![agentmods](https://agentmods.dev/badge/skills/dentiny/kon/orchestrator-voice.svg)](https://agentmods.dev/skills/dentiny/kon/orchestrator-voice)
Your own site
<a href="https://agentmods.dev/skills/dentiny/kon/orchestrator-voice"><img src="https://agentmods.dev/badge/skills/dentiny/kon/orchestrator-voice.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 608 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.00608
Opus 5 $0.00023 $0.00304
Sonnet 5 $0.00009 $0.00122
Haiku 4.5 $0.00005 $0.00061

Measured 8d ago against content hash dc07f51fae93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

orchestrator-voice 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 8d 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.

skills/orchestrator-voice/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator Voice

Owner: orchestrator Consumers: all /kon:* commands (used alongside skills/narration — narration governs the narrator-beat ritual, this skill governs the conversational body)

Core principles (always): follow skills/core-principles — first principles (don't hide the issue); simplest, most concise correct solution.

Output compression: when /caveman is active, apply skills/caveman to all chat prose. Artifact files and hook-validated sections are never compressed.

Widget discipline

AskUserQuestion only when options are converged and the user is just deciding.

When design or direction is still open (user asks "why / should we / is there a better way?"), talk it through in prose first — give a recommendation with tradeoffs — don't jump to a widget to force a choice.

  • Options converged (confirm / binary choice / multi-select list) → widget is fine
  • Direction still open / question is still exploratory → prose first, widget only if needed after
  • When a widget is dismissed without an answer: do not re-show the same widget — rephrase in plain text and ask again
  • If answers is empty (user closed the widget without answering): do not treat this as "skip" and continue — ask again in plain text

Why: widgets interrupt thinking when options aren't settled yet. Users often advance with a single word ("yes" / "go" / "that one") — no widget needed.

When receiving "make it more in-character" requests

When the user says something like "make it more character-like" / "closer to the source" / "more personality" — clarify the layer before acting. Ask:

  • Document layer: first impression in docs (cast page, README table, character intro text)
  • Execution layer: the tone of agent turns during actual runs (agent prompt voice, typical lines, emoji prefix)

These are different work. Clarify which one (or both) before writing a plan. Put the other layer in Non-goals.

Read the full file on GitHub · 46 lines

Changes

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.

  1. 8d ago First seen · 46 lines · 45 tokens per session scan A dc07f51fae93

Subscribe to this mod's changes

orchestrator-voice is a skill published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 608 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens