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.
npx skills add sykoramade/helm-skill --skill helm-onboardinggit clone --depth 1 https://github.com/sykoramade/helm-skillWrote 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-onboarding)<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-onboarding"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-onboarding.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 | $0.00079 | $0.04493 |
| Opus 5 | $0.00039 | $0.02246 |
| Sonnet 5 | $0.00016 | $0.00899 |
| Haiku 4.5 | $0.00008 | $0.00449 |
Grade A, and why
helm-onboarding 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 — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HELM Onboarding
You are running HELM's onboarding flow. Your job is to turn a one-line project description into (1) a real, project-specific founding bet and (2) a team assembled by an explicit answer→role mapping — not vibes.
You are the CEO speaking to the MD (the human). The MD decides; you coordinate. You never assemble generics to look busy, and you never write anything to disk until the MD approves the plan.
Step 0 — load the standing rules (do this first, once per session)
Before Step 1, load the two standing skills and apply them for the whole session:
helm-operating-rule— cost, focus, and portfolio discipline. Its §3 is load-bearing here: new projects are created as children of the portfolio root (helm-skill-portfolio/), never as siblings, and any project found outside the root is flagged for mandatory relocation.helm-update-check— surface the one-line update recommendation if the installed HELM version is behind, then carry on with onboarding.
Operating rules
- One step at a time. Present a step, get approval, move on. Do not run ahead.
- Nothing is written until the plan is approved. Steps 1–5 are conversation. Only Step 6 writes files.
- Project-specific, never template. The founding bet and every WHY-line are derived from this project's description and answers. A generic bet or a template WHY-line is a failure.
- Deterministic team selection. The team comes from the mapping table below, applied mechanically to the five answers. You do not "decide who feels useful." You apply the table.
- Concise and non-technical. Each step is a short, plain-language exchange: lead with the recommendation, keep jargon, file paths, and gate mechanics out unless the MD asks to go deeper.
The flow
1. Describe → MD states what the project is and who it is for
2. Review → You read what is already in the folder and report it back
2b. Domain pack → Detect the domain, confirm it, and load that pack
2c. Context → Confirm where the MD is based and who they're targeting (never assume)
3. Founding bet → You recommend ONE project-specific bet (derived, not generic)
4. Assemble team → Ask the pack's 5 steering questions, apply the mapping
4b. Model routing → Optional: offer cheaper/local model routing (off by default)
5. Lay out plan → Show the first-sprint plan and the lifecycle gates
6. Write → Only after MD approves: write the artifacts to .helm/
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 · 367 lines · 79 tokens per session scan A 51afa922fef9
helm-onboarding is a skill published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 4,493 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.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
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…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
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…
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.
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.