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 vanzan01/claude-agent-sdk-starter --skill analysis-helpergit clone --depth 1 https://github.com/vanzan01/claude-agent-sdk-starterWrote 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/vanzan01/claude-agent-sdk-starter/analysis-helper)<a href="https://agentmods.dev/skills/vanzan01/claude-agent-sdk-starter/analysis-helper"><img src="https://agentmods.dev/badge/skills/vanzan01/claude-agent-sdk-starter/analysis-helper.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 | $0.00010 | $0.00368 |
| Opus 5 | $0.00005 | $0.00184 |
| Sonnet 5 | $0.00002 | $0.00074 |
| Haiku 4.5 | $0.00001 | $0.00037 |
Grade A, and why
analysis-helper 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.
What it actually says
Analysis Helper
CRITICAL: Output Format
You receive JSON input, but you MUST output PLAIN TEXT (not JSON).
Your output MUST look EXACTLY like this:
Winner: [copy the exact title from input]
Why it matters: [2-3 sentences explaining significance]
WRONG vs CORRECT
WRONG - JSON output (DO NOT DO THIS):
{ "winner": { "title": "...", "why_it_matters": "..." } }
WRONG - Markdown:
**Winner:** Some headline
CORRECT - Plain text only:
Winner: OpenAI releases GPT-5
Why it matters: This is significant because it represents a major leap in AI capabilities.
Rules
- Output starts with
Winner:(plain text, no asterisks) - Then
Why it matters:(plain text, no asterisks) - NO JSON - do not output curly braces {} or square brackets []
- NO markdown - do not use ** or ## or ` or _
- NO code blocks - do not wrap output in ```
- Just two lines of plain text
BEFORE YOU OUTPUT - CHECK:
❌ Does my output contain { or } or [ or ]? → REMOVE THEM ❌ Does my output contain ** or ## or ``? → REMOVE THEM ❌ Does my output start with anything other than "Winner:"? → FIX IT ❌ Is my output wrapped in code blocks ```? → REMOVE THE BLOCKS ✅ Is it EXACTLY: "Winner: [title]\nWhy it matters: [explanation]"? → GOOD!
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 56 lines · 10 tokens per session scan A 6209284ce6c0
analysis-helper is a skill published in the GitHub repository vanzan01/claude-agent-sdk-starter (9 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 368 once invoked, about $0.0001 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
frontmcp-deployment
Use when deploying, building for production, packaging, or shipping a FrontMCP server. Covers build targets (node, cli SEA binary, browser, embeddable SDK, mcpb archive for Claude Desktop, serverless) and deploying to Vercel (with Vercel KV), AWS Lambda (API Gateway, SAM, CDK), Cloudflare Workers (KV, D1, Durable…
pipefy-ai-agents
Use this skill when the user wants to create, read, update, delete, or troubleshoot AI agents (conversational agents with behaviors). Covers 7 MCP tools including pre-flight validation, plus pipe-scoped knowledge bases (list, plain text/document/data lookup CRUD, access probe) attached via dataSourceIds. For…
huawei-ecs
Use when creating, configuring, managing, or troubleshooting ECS instances on Huawei Cloud. Covers instance creation (hcloud ECS CreateServers), flavor selection, image management, security groups, EIP binding, disk attachment, auto-scaling (AS), and troubleshooting. Triggers on: ECS, instance, flavor, image, security…
huawei-rds
Use when creating, configuring, managing, or troubleshooting RDS instances on Huawei Cloud. Covers MySQL, PostgreSQL, SQL Server. Triggers: RDS, MySQL, PostgreSQL, database instance, backup, read replica. NOT for: GaussDB (use huawei-gaussdb), DDS (use huawei-dds-dcs).
pipefy-automations
Use this skill when the user wants to create, read, update, or delete traditional automations (if/then rules) or AI automations (prompt-driven). Covers 16 MCP tools. For AI agents (conversational), see skills/ai-agents/.
huawei-cce
Use when creating or managing CCE Kubernetes clusters. Covers cluster creation, node pools, SWR registry, autoscaling. Triggers: CCE, Kubernetes, K8s, cluster, node pool, container, SWR. NOT for: serverless functions (use huawei-functiongraph), serverless containers (use huawei-cce for CCI redirect).