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 staruhub/CrewClaw --skill roi-estimatorgit clone --depth 1 https://github.com/staruhub/CrewClawWrote 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/staruhub/crewclaw/roi-estimator)<a href="https://agentmods.dev/skills/staruhub/crewclaw/roi-estimator"><img src="https://agentmods.dev/badge/skills/staruhub/crewclaw/roi-estimator/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/staruhub/crewclaw/roi-estimator"><img src="https://agentmods.dev/badge/skills/staruhub/crewclaw/roi-estimator.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 | $0.00024 | $0.00176 |
| Opus 5 | $0.00012 | $0.00088 |
| Sonnet 5 | $0.00005 | $0.00035 |
| Haiku 4.5 | $0.00002 | $0.00018 |
Grade A, and why
roi-estimator 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.
What it actually says
ROI Estimator
Overview
Estimate ROI with structured, honest assumptions — investment, benefit hypotheses, and risks — not a single confident number.
When to Use
When the user wants a business case for adopting AI in a workflow.
Workflow
- List the investment: model/API cost, build effort, maintenance.
- List benefit hypotheses: time saved, quality lift, capacity gained — each as a range.
- Compute a rough ROI range from the assumptions; show the formula.
- State the top risks/uncertainties; mark unverified numbers as [placeholder].
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 · 25 lines · 24 tokens per session scan A 59d29c3b1f07
roi-estimator is a skill published in the GitHub repository staruhub/CrewClaw (22 stars, last pushed 3d ago), licensed Apache-2.0. It adds 24 tokens to every session and 176 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 2026-08-30.
Other skills, from other repositories
comparable-company-analysis
A workflow for comparing a publicly listed company with similar listed companies. It examines their businesses, financial results, competitors, and recent developments.
财经分析工具包
A set of finance analysis tools for stocks, markets, portfolios, and financial news. It includes data retrieval, technical indicators such as moving averages and RSI, trend analysis, risk assessment, and allocation suggestions.
payment-session
Streaming + recurring billing for OpenClaw agents over x402 — meter pay-as-you-go usage or run a subscription, settle in batches through payx402, with a hard per-session spend cap. Non-custodial.
parad0x-mcp-server
MCP server exposing the full Parad0x Labs stack — x402 payment quotes, on-chain receipt anchoring on Solana mainnet-beta, Dark Passport lookup, outcome receipts, receipt compression, and live program discovery. Runs over stdio, works with Claude Desktop and any MCP client.
dna-payment-bridge
Bridges DNA x402 micropayment audit logs and signed receipts into Liquefy vaults as verifiable proof artifacts. Exports audit events, converts receipts to proof artifacts, and optionally anchors each receipt hash on Solana via an SPL Memo transaction.
openclaw-x402-pay
Pay x402-gated APIs and AI agents on Solana — builds an unsigned payment transaction, verifies settlement on-chain, and returns a receipt hash. Hard spend cap enforced before any transaction. BYO signer, no keys held.