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 agentmods add skills/taskfuel/skills/lead-prospectingnpx skills add taskfuel/skills --skill lead-prospectinggit clone --depth 1 https://github.com/taskfuel/skillsWrote 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/taskfuel/skills/lead-prospecting)<a href="https://agentmods.dev/skills/taskfuel/skills/lead-prospecting"><img src="https://agentmods.dev/badge/skills/taskfuel/skills/lead-prospecting.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 | $0.00065 | $0.02071 |
| Opus 5 | $0.00032 | $0.01035 |
| Sonnet 5 | $0.00013 | $0.00414 |
| Haiku 4.5 | $0.00006 | $0.00207 |
Grade A, and why
lead-prospecting 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 3d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lead Prospecting
ICP → companies → the right person at each, as a CSV of leads (ICP-matched contacts,
not qualified prospects). Email lookup and deliverability are the companion
email-verification skill, handed off after Step 3. Never drafts or sends outreach.
Prerequisites
taskfuelCLI connected (taskfuel whoami), balance ≥ ~$0.35 for a full discover run.- Base
taskfuelskill covers payment mechanics — quote with--dry-run, pay with--max-amount, never suppress stderr on a paid call. Read it first if you haven't.
Rules
- Prompt, never guess. Ask for each step's parameters with examples so answering takes one word. Guessed ICPs and job functions return wrong results or none.
- Announce cost, then wait for OK. Never chain straight into a paid call. Confirm before any step adds >~50 rows.
- Seller-agnostic — no built-in ICP. Fit criteria come only from the user's own words; never assume what is being sold.
Intake
- Entry point: discover (Step 1), or bring-your-own domains — skip Step 1, seed the table from the pasted domains, start at Step 2.
- In discover mode, pick the route from the shape of the ICP — never ask the user to name
a tool:
- Categorical / numeric (an industry, a country, a headcount band) → route A.
- Thematic / semantic ("customer-support automation", "cross-border payroll") → route B.
FullEnrich's 490-value industry enum has no agent/AI entry — its documented stand-ins
(
Software Developmentfor SaaS,Research Servicesfor AI labs) are far wider than the theme. - Both kinds given → route B to find them, then filter on the numbers client-side.
- Fit criteria (optional): "What are you selling, and what makes a company a good fit?" Free text. Blank ⇒ skip Step 1b and present unranked.
Deliverable
leads-YYYY-MM-DD.csv, written at the first data step and enriched in place. Nothing
discarded — one row per person, plus a placeholder row per contactless company. Selected?
marks the primary contact; the rest stay as fallbacks. All rows go to the CSV; show only a
top slice in chat.
What ships with it
3 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.
- 3d ago First seen · 146 lines · 65 tokens per session scan A 6ec7d01fdc15
lead-prospecting is a skill published in the GitHub repository taskfuel/skills (2 stars, last pushed 5d ago), licensed MIT. It adds 65 tokens to every session and 2,071 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
image-prompting
Use when generating or editing images via blockrunimage — especially with GPT Image 2, Nano Banana, or Grok Imagine for posters, UI mockups, marketing assets, product shots, or anything with on-image text. Turns vague user requests ("make me a cool poster") into structured, text-accurate prompts that actually render…
surf
Use when the user wants crypto data — token prices, on-chain SQL, prediction-market positions, CEX order books, wallet labels/net-worth, social mindshare, news, or unified search. 83 endpoints across exchange, on-chain, wallet, social, prediction, news and search — one API, flat $0.0085/call in USDC via x402. Settles…
blockrun
Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana). No API keys, no accounts, no subscriptions. Start here when you have the BlockRun MCP installed and need to know WHICH tool answers a question, how the wallet works, or how to make a…
gentech-blockrun
GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent. Covers daily usage patterns, cost-optimized workflows, multi-tool pipelines, and reliable error handling for BlockRun's full toolset.
search
Use when the user wants real-time web or news results with AI-summarized answers and citations — Grok Live Search via BlockRun. Cheapest path for "what just happened" questions where freshness beats neural-semantic ranking.
blockrun-setup
Use when asked to install, add, configure, or set up the BlockRun MCP server (@blockrun/mcp) in Claude Code, Claude Desktop, Cursor, Windsurf, Codex CLI or another MCP client — including first-run wallet creation, funding with USDC, choosing a tool profile, and proving the install works. Also use when a fresh install…