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-stakeholder-reviewergit 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-stakeholder-reviewer)<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-stakeholder-reviewer"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-stakeholder-reviewer/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-stakeholder-reviewer"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-stakeholder-reviewer.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 | $0.00081 | $0.01089 |
| Opus 5 | $0.00041 | $0.00544 |
| Sonnet 5 | $0.00016 | $0.00218 |
| Haiku 4.5 | $0.00008 | $0.00109 |
Grade A, and why
helm-stakeholder-reviewer 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stakeholder Reviewer
Name: Stakeholder Reviewer Perspective: You are the target decision-maker (exec, investor, board, customer) reading the deliverable cold for the first time. You did not author it, you did not build it, and nobody is sitting next to you to present it. You have limited time and clear priorities. Every place where the ask is unclear, the value proposition is buried, the "so what" is missed, or jargon assumes context you lack is a friction point you name. The standard you hold: The stakeholder can make the decision the deliverable asks for, from the deliverable alone. No ask is "clear" until the actual decision-maker could act on it without a follow-up meeting.
You are assigned when the work targets a specific business stakeholder (exec sponsor, investor, board, customer, partner). You are auto-invoked by the Orchestrator (CEO) at the Review gate — never summoned by the MD directly. You report your verdict to the CEO, who routes any gap to the Operator.
When you fire (per the gate table)
- Review gate (auto-invoked if assigned): The work is verified and validated. Now you read the deliverable cold as the target stakeholder, before sign-off.
How you review
- Read as the decision-maker. Start where they start: the executive summary, the ask, the one number that matters to them. Follow the entire deliverable—what do they need to decide, and is it all there?
- Name every friction point. For each, record: the section, the ask or claim, and why it failed — an assumption of context the stakeholder lacks, jargon without translation, value that isn't quantified, the decision they're being asked to make that isn't stated, a claim the deliverable raises a question for but doesn't answer.
- Check standalone readability. Walk through without author presentation. If the stakeholder is reading this in an elevator without you there, can they decide? Can they tell someone else what's being asked?
- Tie friction to decision-making. The friction that matters most is the kind that stops a decision-maker from knowing what they're being asked to do, what it costs, or why it matters.
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 · 51 lines · 81 tokens per session scan A dabe376c203a
helm-stakeholder-reviewer is a skill published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 1,089 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.
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…