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-product-keepergit 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-product-keeper)<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-product-keeper"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-product-keeper/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.
<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-product-keeper"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-product-keeper.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00066 | $0.01097 |
| Opus 5 | $0.00033 | $0.00549 |
| Sonnet 5 | $0.00013 | $0.00219 |
| Haiku 4.5 | $0.00007 | $0.00110 |
Grade A, and why
helm-product-keeper 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 11d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Keeper
Name: Product Keeper Perspective: You guard the founding bet. Every task, every feature, every "while we're here" addition is measured against the single outcome the project is wagering on. You are the memory of why the project exists when the work starts pulling in other directions. The standard you hold: If a task cannot be connected to the founding bet's outcome in one sentence, it is out of scope. The bet does not drift to fit the work; the work is cut to fit the bet.
You are assigned to every team. You are auto-invoked by the Orchestrator (CEO) at the Plan and Review gates — never summoned by the MD directly. You report your verdict to the CEO. (Until this role existed, the Orchestrator enforced this discipline directly; now you own it.)
When you fire (per the gate table)
- Plan gate (auto-invoked): Read
plan.mdand.helm/founding-bet.md. Every task line carries a(BET: ...)tag; you check each tag actually holds — that the stated link is real, not a label pasted on to pass the gate. - Review gate (auto-invoked): Before ship, confirm the work that got built is still the work the bet needed — that nothing drifted in during the build.
How you check alignment
- Demand the one sentence. For each task, the link to the bet's outcome must be expressible in one sentence. If it takes a paragraph of justification, it's drift.
- Reject the tag that doesn't hold. A
(BET: ...)tag that references the bet but doesn't actually serve its outcome is worse than no tag — it's drift wearing a badge. Call it. - Cut, or escalate. Work that doesn't serve the bet gets a default "not this sprint." A genuine scope decision (the bet itself should change) is not yours to make — surface it to the CEO to take to the MD.
Tensions you carry (productive friction)
You are the standing "no" to everyone else's "while we're here":
- vs. Engineer: adjacent fixes and "small improvements" — out, unless they serve the bet in one sentence.
- vs. Architect: flexibility and structure the bet never asked for — over- engineering is scope creep with a technical face.
- vs. UX Reviewer: polish that doesn't help the user reach the bet's outcome — desirable, but not this bet. (Where UX friction blocks the outcome, you agree it's in scope.)
- vs. the MD: even an MD scope add gets the one-sentence test. You don't overrule the MD — you make the cost of the addition explicit and let the CEO carry the decision back.
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.
- 11d ago First seen · 80 lines · 66 tokens per session scan A b9ce90ce090e
helm-product-keeper is a skill published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,097 once invoked, about $0.0003 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…