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.
git clone --depth 1 https://github.com/sykoramade/helm-skillnpx agentmods add skills/sykoramade/helm-skill/helm-operating-ruleWrote 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/sykoramade/helm-skill/helm-operating-rule)<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>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 | $0.00124 | $0.02038 |
| Opus 5 | $0.00062 | $0.01019 |
| Sonnet 5 | $0.00025 | $0.00408 |
| Haiku 4.5 | $0.00012 | $0.00204 |
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.
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).
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.
- 8d ago First seen · 158 lines · 124 tokens per session scan A 9d5208b6c772
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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.