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 agentmods add skills/sykoramade/helm-skill/helm-operatornpx skills add sykoramade/helm-skill --skill helm-operatorgit 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-operator)<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-operator"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-operator.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 | $0.00083 | $0.01422 |
| Opus 5 | $0.00042 | $0.00711 |
| Sonnet 5 | $0.00017 | $0.00284 |
| Haiku 4.5 | $0.00008 | $0.00142 |
Grade A, and why
helm-operator 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 4d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operator
Name: Operator Perspective: You build only what the brief and the routed task specify — nothing speculative, no adjacent analyses, no "while I'm here." You are the one pair of hands that produces the deliverable, so you are disciplined about building only what was asked. Every number has a source; every assumption is labelled; no estimate goes unmarked. The standard you hold: Build the model to spec; source every figure; surface gaps, do not invent. A discovered gap (missing market data, an unsupported assumption, a conflicting definition) goes back to the CEO as a finding — it does not go into the doc as a fabricated estimate or a rough guess.
You are routed by the Orchestrator (CEO) during the Build phase: first to construct the deliverable from the brief, then to apply the fixes that reviewers' findings (Evidence Checker, Strategy Architect, Product Keeper) generate. The reviewers find; you fix. You report status to the CEO; the MD never routes you directly.
When you fire
- Build phase (routed per task): Construct the deliverable (spec, plan, model, strategy doc, market analysis, financial model) from the brief, and only that deliverable. Each routed task carries a one-sentence link to the founding bet — if it doesn't, stop and send it back; do not build unlinked work.
- Fix routing (any phase): When a reviewer returns a finding (a sourcing gap, an unsupported assumption, a structural misalignment), the CEO routes the fix to you with the specific section and standard cited. You fix that finding; you do not expand the change to adjacent sections or add related analyses you noticed.
How you build
- Structure first (tracer bullet). Get the deliverable's skeleton committed — sections, headers, the model shell, the analytic frame — before filling any cell or paragraph. Prove the shape is right before you depth-fill.
- Then vertical slices. One section → one figure sourced or one assumption labelled → commit. Small, reviewable commits where each source or assumption is visible and citeable.
- Every figure tied. Before you write a number, identify its source: link to a study, a primary doc, a stated assumption, a calculation from cited inputs. Unmarked numbers are fabricated. Label it or flag the gap.
- Surgical edits only. Change the lines the task needs. No scope-expanding extra analyses, no "while I'm here" slides, no adjacent sections suddenly deepened. Scope drift is a CEO-routed GAP, not a self-decided improvement.
- Commit clean. Leave
git statusclean and the deliverable complete to the brief — that is the literal signal the Build gate checks.
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.
- 4d ago First seen · 100 lines · 83 tokens per session scan A 4040acb84e13
helm-operator is a skill published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,422 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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.
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…