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 DariuszCiesielski/polish-agent-skills --skill craig-lead-research-plgit clone --depth 1 https://github.com/DariuszCiesielski/polish-agent-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/dariuszciesielski/polish-agent-skills/craig-lead-research-pl)<a href="https://agentmods.dev/skills/dariuszciesielski/polish-agent-skills/craig-lead-research-pl"><img src="https://agentmods.dev/badge/skills/dariuszciesielski/polish-agent-skills/craig-lead-research-pl/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/dariuszciesielski/polish-agent-skills/craig-lead-research-pl"><img src="https://agentmods.dev/badge/skills/dariuszciesielski/polish-agent-skills/craig-lead-research-pl.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 | $0.00206 | $0.04548 |
| Opus 5 | $0.00103 | $0.02274 |
| Sonnet 5 | $0.00041 | $0.00910 |
| Haiku 4.5 | $0.00021 | $0.00455 |
Grade A, and why
craig-lead-research-pl 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 12d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lead Research — polski SaaS B2B (micro-small)
Źródło: Adaptacja z TheCraigHewitt/skills/sales/lead-research (Craig Hewitt, founder Castos). Wycięto enterprise (ZoomInfo, 6sense, Bombora, multi-stakeholder power maps 5+ osób). Dodano polskie źródła i realia micro-small SaaS.
Przed startem
Sprawdź czy istnieje .agents/sales-context.md — zawiera ICP, value prop, proof points. Jeśli brak — uruchom skill sales-context najpierw albo podaj te informacje ręcznie. Bez ICP każdy research to strzał w ciemno.
7 zasad fundamentalnych
- Trigger events biją zimne listy. Firma która właśnie dostała finansowanie PFR, zatrudniła nowego CMO albo otworzyła nowe biuro jest 5x bardziej responsive niż losowy ICP-fit. Zawsze zaczynaj od triggerów.
- Badaj konto, nie tylko kontakt. Kontekst firmy (etap wzrostu, stack, ostatnie ruchy) znaczy więcej niż email. Kontekst sprawia że outreach brzmi sensownie.
- Power maps wygrywają deale — ale dla polskiego micro-SaaS to max 2-3 osoby. W enterprise mapujesz 5 ról (economic buyer, champion, evaluator, blocker, coach). W polskich firmach 10-50 osób często 1 osoba decyzyjna + 1 champion. Nie wymyślaj struktury której nie ma.
- Tieruj konta bezwzględnie. Tier 1 = deep research + multi-channel. Tier 3 = szablon. Czas per lead musi pasować do wartości deala.
- Research ma wartość tylko jeśli dociera do Ciebie w formie action. Struktured brief, 60 sekund na przeskanowanie. Wall of notes to porażka.
- Job postings to najbardziej niedoceniane źródło sygnałów w B2B. Ogłoszenie rekrutacyjne mówi Ci: stack techniczny, priorytety, budżet, skład zespołu, trajektorię wzrostu — wszystko w jednym miejscu. W Polsce: justjoin.it, nofluffjobs.com, pracuj.pl, rocketjobs.pl. Zacznij od nich, potem corroboruj.
- LinkedIn Sales Navigator > baza danych. LinkedIn SN daje Ci kontekst (co publikują, z kim wchodzą w interakcje, co ich obchodzi, ciepłe ścieżki przez wspólne kontakty). Baza danych daje Ci tylko adres email. Kontekst bez danych > dane bez kontekstu.
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.
- 12d ago First seen · 239 lines · 206 tokens per session scan A 009925ebb542
craig-lead-research-pl is a skill published in the GitHub repository DariuszCiesielski/polish-agent-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 206 tokens to every session and 4,548 once invoked, about $0.0010 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
Error Message Reviewer
Audit error messages across an application for clarity, actionability, consistency, and user-friendliness by cataloging and grading every error surface.
roblox-input
Use when handling Roblox keyboard, mouse, gamepad, touch, motion input, or cross-platform action binding.
roblox-lighting
Use for Roblox lighting, atmosphere, day/night, or post-processing effects.
roblox-luau-core
Use for Luau language semantics, tables, control flow, string patterns, scope, closures, and cross-language translation errors.
roblox-performance
Use when profiling Roblox performance or diagnosing FPS, memory, network, mobile, or hot-path problems.
roblox-server-data
Use for Roblox server or cross-server data: OrderedDataStore leaderboards, MessagingService, world state, seasons, or guilds.