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 WebhoundAI/webhound-mcp --skill webhound-researchgit clone --depth 1 https://github.com/WebhoundAI/webhound-mcpWrote 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/webhoundai/webhound-mcp/webhound-research)<a href="https://agentmods.dev/skills/webhoundai/webhound-mcp/webhound-research"><img src="https://agentmods.dev/badge/skills/webhoundai/webhound-mcp/webhound-research.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 | $0.00054 | $0.01202 |
| Opus 5 | $0.00027 | $0.00601 |
| Sonnet 5 | $0.00011 | $0.00240 |
| Haiku 4.5 | $0.00005 | $0.00120 |
Grade A, and why
webhound-research 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Webhound research
Use Webhound when the cost of missing information is greater than the cost of doing more research. Use a quicker tool for simple factual lookups.
Research contract
- The prompt says what to investigate. The dollar budget says how much effort the investigation deserves.
- Hound is Webhound's research harness built with DeepSeek V4 Pro and GPT-5.4 across planning, execution, verification, and assembly.
- Hound is not a selectable model or mode, and it is not a direct pass-through to one provider.
- A larger budget should buy more searching, reading, comparison, verification, and evidence—not just a longer answer.
- Every user authorizes Webhound with their own account and API key. Never embed, share, or reuse a publisher's, teammate's, or other user's credential.
Before starting
- If the hosted Webhound server needs authentication, ask the user to complete Webhound sign-in and consent in the client's OAuth flow. Each person connects their own Webhound account. Local stdio installs instead use that user's own generated Webhound API key.
- Confirm the research question, desired artifact, and dollar budget. Starting a report, dataset, or budget extension can spend money, so do not invent or silently increase a budget.
- Use a report for a cited argument, comparison, map, or recommendation. Use a dataset for rows, fields, and per-field provenance.
- If the user wants guidance, recommend $2 for quick scouting, $5 for normal cited research, $10 for deep work, or $20 for exhaustive/highest-stakes work. These are starting points, not caps or permission to spend; the user can choose a larger custom budget for longer, deeper research. Roughly, $1 buys about 15 minutes, so $5 is about 75 minutes and $20 is about 300 minutes (five hours). Actual runtime still varies.
- A new account may have one indivisible free run for one exact $5 report or dataset. Check account or onboarding status rather than promising it. Honor the saved preference: use it automatically only when enabled, or after the user explicitly consents to use it for this exact $5 run.
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 · 98 lines · 54 tokens per session scan A 6df7020f2a77
webhound-research is a skill published in the GitHub repository WebhoundAI/webhound-mcp (1 stars, last pushed 20d ago), licensed MIT. It adds 54 tokens to every session and 1,202 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
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
apollo-lead-finder
Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…