helm-operating-rule

helm-operating-rule is a skill for Claude Code from sykoramade/helm-skill. It costs 124 tokens per session (2,038 once invoked), scanned A, original, MIT.

A standing set of rules for running HELM projects, covering spending, focus, project structure, and honest completion claims.

In plain words
What is it for?
It guides model routing, checks whether tasks support the project's founding bet, keeps work within the right portfolio, and requires proof before declaring completion.
Why use it?
It helps prevent wasted work, scope drift, misplaced tasks, and claims that a job is finished without evidence.

Skill for Claude Code

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

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is {"ts": "2026-06-25T10:00:00Z", "event": "relocation_pending", "project": "verita-factcheck", "found_at": "../helm-skill-test", "target": "helm-skill-portfolio/v.

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

Good fit It guides model routing, checks whether tasks support the project's founding bet, keeps work within the right portfolio, and requires proof before declaring completion.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/sykoramade/helm-skill
agentmods
npx agentmods add skills/sykoramade/helm-skill/helm-operating-rule

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-operating-rule

README.md
[![agentmods](https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-operating-rule.svg)](https://agentmods.dev/skills/sykoramade/helm-skill/helm-operating-rule)
Your own site
<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-operating-rule"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-operating-rule.svg" alt="Measured on agentmods" height="20"></a>
Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,038 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 $0.00124 $0.02038
Opus 5 $0.00062 $0.01019
Sonnet 5 $0.00025 $0.00408
Haiku 4.5 $0.00012 $0.00204

Measured 8d ago against content hash 9d5208b6c772, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

helm-operating-rule 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/helm-operating-rule/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HELM Operating Rule — Cost, Focus & Portfolio Discipline

Standing rule for the HELM pack. Applies to the Orchestrator and every agent for the whole session — the entry-point skills (helm-orchestrator, helm-onboarding, helm-portfolio) load it first. These are enforced defaults, not suggestions. When a rule says "STOP and ask," surface a one-line check to the MD before spending more tokens.

These four policies sharpen rules HELM already holds: the CEO never executes the work (helm-orchestrator), every task traces to the founding bet (helm-product-keeper), projects nest under a portfolio root (helm-portfolio), and a completion claim is not a fact until its evidence is shown (helm-verification-before-completion). This skill makes the cost, focus, structure, and completion-honesty edges of those rules mechanical and citable.


1. Model Routing — the orchestrating model never does grunt work

Default: the main-loop / orchestrating model orchestrates, decides, and reviews only. It must NOT execute mechanical work inline. Mechanical work is delegated to a cheaper tier via subagent (a strong build model for real work, a cheap deterministic model for cheap deterministic steps).

Grunt work (ALWAYS offload): file/format conversion, zipping/packaging, scaffolding, find-and-replace, boilerplate, running builds/tests/linters, doc/report generation, dependency installs, log/format tidy-ups, and retrying flaky tooling.

Stays on the strong model (do NOT offload): work that is risky or complex — architectural decisions, ambiguous requirements, security/secrets/keys, irreversible or destructive operations, cross-cutting design, or anything where being wrong is expensive. This is the same line HELM already draws at the gates: gate-critical work (Counterweight, the Integrity reviewer, the Verification reviewer, anything you would ESCALATE-TO-MD) never goes to a cheap tier (helm-model-router §4).

Hard trigger: if you catch yourself on the 2nd inline mechanical retry of the same step, STOP — delegate it to a subagent or hand it back. Never grind a deterministic task across many orchestrator round-trips (each turn re-reads full context at the top tier's rate; the round-trips, not the compute, are the cost).

Read the full file on GitHub · 158 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 · 158 lines · 124 tokens per session scan A 9d5208b6c772

Subscribe to this mod's changes

helm-operating-rule is a skill published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 124 tokens to every session and 2,038 once invoked, about $0.0006 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.