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-outbound-sequence-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-outbound-sequence-pl)<a href="https://agentmods.dev/skills/dariuszciesielski/polish-agent-skills/craig-outbound-sequence-pl"><img src="https://agentmods.dev/badge/skills/dariuszciesielski/polish-agent-skills/craig-outbound-sequence-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-outbound-sequence-pl"><img src="https://agentmods.dev/badge/skills/dariuszciesielski/polish-agent-skills/craig-outbound-sequence-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 | $0.00171 | $0.04663 |
| Opus 5 | $0.00086 | $0.02331 |
| Sonnet 5 | $0.00034 | $0.00933 |
| Haiku 4.5 | $0.00017 | $0.00466 |
Grade A, and why
craig-outbound-sequence-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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outbound Sequence Design — polski SaaS B2B
Źródło: Adaptacja z TheCraigHewitt/skills/sales/outbound-sequence. Wycięto: 10+ rep team management, SEP tool comparison enterprise, 60-day enterprise play. Dodano: polskie reply rate benchmarks, solo founder capacity math, krótszy cykl decyzyjny polskich micro-SaaS.
Przed startem
Sprawdź .agents/sales-context.md — ICP, value prop, sales motion. Bez tego sequence to strzał w ciemno.
Capacity math — policz zanim projektujesz
Przed pojedynczym touch'em zrób matematykę od celu spotkań wstecz. To oddziela strategię outbound od "wysyłajmy maile i miejmy nadzieję".
Miesięczny cel spotkań: ___
÷ Expected meeting rate: ___% (benchmarks niżej)
= Kontakty do sequence/miesiąc: ___
Przykład polskiego solo foundera:
Cel: 5 spotkań/miesiąc
Meeting rate: 5% (personalized multi-channel)
→ 100 kontaktów do sequence/miesiąc
Przy 14-dniowej sekwencji:
→ ~50 aktywnych kontaktów w każdym momencie
→ ~5 nowych kontaktów dziennie (25 dni roboczych)
Meeting rate benchmarks (PL SaaS micro-small):
| Podejście | Meeting rate | Kontaktów na 5 spotkań |
|---|---|---|
| Personalized multi-channel | 4-6% | 85-125 |
| Semi-personalized email + LinkedIn | 2-4% | 125-250 |
| Templated email-only | 0.5-1.5% | 335-1000 |
| Warm/triggered outbound | 8-15% | 35-65 |
Polski realizm: jeśli Twoja matematyka mówi "potrzebuję 500 kontaktów/miesiąc" — nie masz problemu z sequence, masz problem ze skalą rynku (polski B2B SaaS micro-small nie ma takich volumes). Celuj w warm/triggered + personalized multi-channel, nie w spray-and-pray.
5 zasad fundamentalnych
- Multi-channel zawsze bije single-channel. Sekwencje tylko-email plateau na ~2% reply rate. Dodaj LinkedIn + telefon → 8-12%. Kanały wzmacniają się nawzajem — Twój email ląduje inaczej po tym jak zobaczyli Twoją wizytę na profilu.
- Front-load intensywność, potem rozrzedź. Dni 1-7 najwyższa density touchy. Jeśli się zaangażują, to zwykle w pierwszym tygodniu. Potem długa gra.
- Każdy touch musi być standalone. Nie pisz "just following up na mój poprzedni email". Każda wiadomość potrzebuje własnego powodu istnienia — nowy insight, inny kąt, świeży trigger. Jeśli nie wymyślasz nowego kąta — brak researchu.
- Wiedz kiedy przestać. Więcej touchy ≠ więcej reply. Po 12-14 touchach zero engagement → nurture track albo inna persona w tej samej firmie. Wytrwałość OK, nękanie NIE.
- Testuj sekwencję, nie tylko wiadomości. Większość testuje subject lines, nigdy struktury sekwencji — timing, kolejność kanałów, liczba touchy. Struktura często waży więcej niż copy.
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 · 346 lines · 171 tokens per session scan A ed173d2aea1f
craig-outbound-sequence-pl is a skill published in the GitHub repository DariuszCiesielski/polish-agent-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 171 tokens to every session and 4,663 once invoked, about $0.0009 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.