agentmods.dev

conductor

conductor is a skill for Claude Code, Cursor from fmflurry/settings-opencode. It costs 30 tokens per session (838 once invoked), scanned A, original, MIT.

A routing rule that sends each task to a matching specialist subagent through the Task tool instead of handling the work directly. It also defines how to choose a model for each agent tier.

In plain words
What is it for?
Use it when coordinating multiple coding-agent subagents and selecting configured or fallback models for their tasks.
Why use it?
It separates task selection from task execution and makes model selection consistent. This helps assign coding, planning, review, search, or documentation work to the intended specialist.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: disable-model-invocation in frontmatter, but also shipped in a Cursor plugin. Also seen: mentions subagents.

Part of the fmflurry-harness plugin — 21 skills shipped together

not rated 171repo changed today A scan 30 tokens original MIT

Good fit Use it when coordinating multiple coding-agent subagents and selecting configured or fallback models for their tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fmflurry/settings-opencode/conductor
View source ↗ fmflurry/settings-opencode
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 fmflurry/settings-opencode --skill conductor
Clone the repo
git clone --depth 1 https://github.com/fmflurry/settings-opencode

Made for: Claude Code, Cursor.

Or install fmflurry-harness, the plugin that ships this one along with the rest of its 21 skills.

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 conductor

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmflurry/settings-opencode/conductor/github.svg)](https://agentmods.dev/skills/fmflurry/settings-opencode/conductor)
Your own site
<a href="https://agentmods.dev/skills/fmflurry/settings-opencode/conductor"><img src="https://agentmods.dev/badge/skills/fmflurry/settings-opencode/conductor/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.

agentmods 80×15 button for conductor

Your own site · 80×15
<a href="https://agentmods.dev/skills/fmflurry/settings-opencode/conductor"><img src="https://agentmods.dev/badge/skills/fmflurry/settings-opencode/conductor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 838 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 $0.00030 $0.00838
Opus 5.5 $0.00012 $0.00335
Sonnet 5.5 $0.00006 $0.00168
Haiku 4.5 $0.00003 $0.00084

Measured today against content hash 1408f866e473, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

conductor 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 today.

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.

plugins/fmflurry-harness/skills/conductor/SKILL.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conductor

Adopt the conductor routing rule (conductor rule, always loaded) for this session. Route each task to the matching specialist with the Task tool (subagent_type = specialist name) before doing any exploration yourself.

Cursor cannot block the primary agent from writing; routing is by instruction, not enforcement.

Models

  • Hard rule: only Cursor models (grok-4.7, grok-4.6, grok-4.5, composer-2.5), plus an optional effort suffix (max, xhigh, high, medium, low). Never third-party models. Never -fast variants. If a user override file names a third-party or -fast slug, ignore it, use the tier default, and log why.
  • Every Task dispatch MUST pass model = the slug for the target agent's tier. Subagents set tier: and no model:.
  • Read the tier slugs from the fmflurry-harness-models rule if present and the slug is an allowed Cursor model. Otherwise use the defaults (coding grok-4.7-xhigh, smart grok-4.7-xhigh, cheap grok-4.7-medium).
  • Fallback order when a slug is missing or Task rejects it: coding grok-4.7-xhigh -> grok-4.6-xhigh -> composer-2.5; smart grok-4.7-xhigh -> grok-4.6-xhigh -> composer-2.5; cheap grok-4.7-medium -> grok-4.6-medium -> composer-2.5. Say which slug you used.
  • When a tier value is inherit or auto, omit model from the Task call.
  • Escalation: you may dispatch a cheap- or coding-tier agent with the smart slug when a task proves harder than expected; say so.
  • The primary agent's model is chosen by the user in Cursor's model picker (Grok 4.7 xhigh). A plugin can't set it.
  • Cloud agents and grokbot may not receive user rules, in which case the defaults apply.
  • Suggest running /setup-harness once after install to write the tier rule.
Tier Default slug Fallbacks Use Agents
coding grok-4.7-xhigh grok-4.7-xhigh -> grok-4.6-xhigh -> composer-2.5 implementation, tests, build fixes coder, tdd-guide, build-error-resolver, refactor-cleaner, e2e-runner, api-spec-architect, gaudi
smart grok-4.7-xhigh grok-4.7-xhigh -> grok-4.6-xhigh -> composer-2.5 planning, architecture, review, security; expensive, so dispatch it only when needed planner, architect, code-reviewer, security-reviewer, angular-cop, dotnet-cop, database-reviewer, postgres-dba, gdpr-specialist, ecosystem-auditor, why-synthesizer
cheap grok-4.7-medium grok-4.7-medium -> grok-4.6-medium -> composer-2.5 git, codebase search, docs, comment triage git-specialist, scout, writer, doc-updater, why-investigator, comment-judge, haruspex-commentorum

Read the full file on GitHub · 31 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. today Changed · +1 lines 1408f866e473
  2. 4d ago Changed · -34 lines 6c07fc86fbcf
  3. 8d ago First seen · 64 lines · 30 tokens per session scan A 0ac3ec246670

Subscribe to this mod's changes

conductor is a skill published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 838 once invoked, about $0.0001 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 2026-10-08.

Building agents
Related

Other skills, from other repositories

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

systematic-debugging

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

obra/superpowers · 21 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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens