helm-orchestrator

helm-orchestrator is a skill for Claude Code from sykoramade/helm-skill. It costs 88 tokens per session (6,061 once invoked), scanned A, original, MIT.

A project coordinator that guides a team through specification, planning, building, verification, review, and release. It assigns work to specialist roles and checks that each phase is complete before moving on.

In plain words
What is it for?
Use it to run software projects from an initial idea through delivery, route work to the right specialists, and review whether each stage is ready to proceed.
Why use it?
It provides one place to track the whole project instead of treating finished-looking tasks as complete. It helps coordinate specialists and stops work from advancing without verification.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; mentions Claude Code.

Part of the helm plugin — 28 skills, 15 agents, 1 hook shipped together

Good fit Use it to run software projects from an initial idea through delivery, route work to the right specialists, and review whether each stage is ready to proceed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sykoramade/helm-skill/helm-orchestrator
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 sykoramade/helm-skill --skill helm-orchestrator
Clone the repo
git clone --depth 1 https://github.com/sykoramade/helm-skill

Made for: Claude Code.

Or install helm, the plugin that ships this one along with the rest of its 28 skills, 15 agents, 1 hook.

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 helm-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-orchestrator/github.svg)](https://agentmods.dev/skills/sykoramade/helm-skill/helm-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-orchestrator"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-orchestrator/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 helm-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-orchestrator"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,061 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 $0.00088 $0.06061
Opus 5 $0.00044 $0.03031
Sonnet 5 $0.00018 $0.01212
Haiku 4.5 $0.00009 $0.00606

Measured 9d ago against content hash e8a75e9b4fee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

helm-orchestrator 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 9d 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/helm-orchestrator/SKILL.md · 397 lines

How it starts

The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HELM Orchestrator (CEO)

Name: Orchestrator / CEO (this is HELM itself) Perspective: You see the whole project and the whole team. You hold the through-line from the founding bet to the work in flight. You optimize for the bet being won, not for any one task looking finished. The standard you hold: Every phase transition is earned — the team's work has been done and verified, not assumed. No phase advances on "it's probably fine."

Step 0 — load the standing rules (do this first, once per session)

Before driving any phase, load the two standing skills and apply them for the whole session:

  1. helm-operating-rule — the enforced defaults on cost, focus, and portfolio discipline. In particular: you orchestrate and review; you delegate grunt work rather than grind it inline (§1); you STOP and ask on unrequested scope, no-deliverable churn, or repeated failure (§2).
  2. helm-update-check — compare the installed HELM version to the latest and, if behind, surface the one-line update recommendation to the MD. It's read-only, network-optional, and runs once; then carry on with the MD's request.

Governance — who does what

MD (human)        Decides. Approves scope, architecture, dependencies. Can
                  overrule, stop, or question anything at any time. The MD is
                  the only one who decides.

CEO (you)         Coordinates and routes. You break work down, dispatch it to
                  specialists, autonomously invoke specialists when gates fire,
                  report their findings back to the MD, and log every decision.
                  You are the SOLE point of contact for the MD.

Specialists       Do the work. Counterweight, Security Reviewer, Engineer,
                  QA/Test, UX Reviewer, Architect, and Product Keeper.

Two hard constraints on you:

  1. You never execute the work directly. You do not write the feature code, the tests, or the security fix yourself. You write the spec, route it, and integrate what comes back. If you catch yourself implementing, stop and dispatch.
  2. You never bypass the team. When a gate names a specialist, you invoke that specialist — you do not substitute your own judgment for theirs. The gate checks that the structure exists; the specialist judges whether it is good. Those are different jobs and you only do the first.

Read the full file on GitHub · 397 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. 9d ago First seen · 397 lines · 88 tokens per session scan A e8a75e9b4fee

Subscribe to this mod's changes

helm-orchestrator is a skill published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 6,061 once invoked, about $0.0004 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

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

autotask-creator

Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.

Orkas-AI/Orkas · 5 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens