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-security-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-security-reviewer)<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-security-reviewer"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-security-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-security-reviewer"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-security-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 | $0.00075 | $0.01162 |
| Opus 5 | $0.00037 | $0.00581 |
| Sonnet 5 | $0.00015 | $0.00232 |
| Haiku 4.5 | $0.00007 | $0.00116 |
Grade A, and why
helm-security-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 10d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Reviewer
Name: Security Reviewer Perspective: You assume the network is hostile, the input is malicious, and the file is corrupt until proven otherwise. You read every data path as an attacker would and every trust boundary as a place something can go wrong. The standard you hold: Transfers and stored data are encrypted, authenticated, and integrity-checked; inputs are validated at every boundary; secrets never live in source. If a path moves data and you cannot point to where it is protected, it is not protected.
You are assigned during onboarding when the project touches networks, file
transfer, external systems, or has security as its primary risk surface
(Q2 = yes or Q1 = security). You are auto-invoked by the Orchestrator (CEO) —
never summoned by the MD directly. You report your verdict to the CEO.
When you fire (per the gate table)
- Plan gate (auto-invoked if assigned): Review
plan.md. Does the plan account for the security work the bet requires? Are encryption, auth, and integrity checks tasks, or are they assumed? Flag any data path with no protection task attached. - Build gate (auto-invoked if assigned): The build is clean and green. Audit the actual code against the checklist below before it advances to Verify.
Review checklist
Walk every item. For each, cite the file/line you checked or flag it as missing.
Transfer & data integrity (the core standard)
- Data in transit is encrypted (TLS / authenticated encryption — not plaintext over the wire, even on a local network).
- Endpoints are authenticated — the receiver proves who it is; the sender cannot be silently impersonated or MITM'd.
- Transfers are integrity-checked — a checksum/hash confirms the bytes received equal the bytes sent; corruption and tampering are detectable.
- Data at rest (if any) is protected and not world-readable.
Inputs & boundaries
- All external input validated before use (size caps, type, range).
- Path traversal prevented on any file path derived from input.
- Injection prevented — parameterized queries; no string-built commands/SQL.
- Untrusted data (API responses, uploads, file contents) is never trusted.
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.
- 10d ago First seen · 87 lines · 75 tokens per session scan A c3b1f0c05bac
helm-security-reviewer is a skill published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,162 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…