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-linkedin-outreach-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-linkedin-outreach-pl)<a href="https://agentmods.dev/skills/dariuszciesielski/polish-agent-skills/craig-linkedin-outreach-pl"><img src="https://agentmods.dev/badge/skills/dariuszciesielski/polish-agent-skills/craig-linkedin-outreach-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-linkedin-outreach-pl"><img src="https://agentmods.dev/badge/skills/dariuszciesielski/polish-agent-skills/craig-linkedin-outreach-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 | $0.00175 | $0.04163 |
| Opus 5 | $0.00088 | $0.02082 |
| Sonnet 5 | $0.00035 | $0.00833 |
| Haiku 4.5 | $0.00017 | $0.00416 |
Grade A, and why
craig-linkedin-outreach-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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Outreach — polski SaaS B2B
Źródło: Adaptacja z TheCraigHewitt/skills/sales/linkedin-outreach. Wycięto: enterprise account-based (50+ kont/Q), team rep management. Dodano: realia polskiego LinkedIn (mniejszy ale B2B aktywny), solo founder volumes, język polskich postów.
Przed startem
Sprawdź .agents/sales-context.md — ICP, value prop, proof points. Bez tego każdy DM to strzał w ciemno.
6 zasad fundamentalnych
- Engage PRZED pitchem. Komentuj posty, reaguj na content, udostępniaj — ZANIM wyślesz request. Twoje nazwisko ma być już znajome kiedy prosisz o cokolwiek.
- Connection request NIE jest pitchem. Request to prośba o połączenie. Pitch przychodzi później (albo wcale). Łączenie tych dwóch = błąd #1 w polskim LinkedIn outreach.
- Pisz jak człowiek, nie jak sekwencja. Wiadomości które brzmią jak automat = ignoring. Jeśli Twoja wiadomość mogłaby być wysłana do 500 osób bez zmian — przepisz.
- Twój profil to landing page. Przed odpowiedzią odwiedzają Twój profil. Jeśli headline to "Założyciel, [firma]" — już przegrałeś. Ma być o wartości którą dajesz ludziom takim jak oni.
- Cierpliwość bije ilość. 20 przemyślanych rozmów > 200 spamowych InMaili. Szczególnie w Polsce — ten rynek jest mały, wszyscy się znają, spam się niesie echem.
- Czytaj sygnały. LinkedIn daje real-time buying signals — profile views, reakcje na posty, accept requesty. Naucz się je czytać i działać.
Polskie benchmarki (przybliżone, rynek mniejszy niż US)
| Metryka | Średnio PL | Dobrze | Bardzo dobrze |
|---|---|---|---|
| Connection accept rate | 25-40% | 40-55% | 55-70% (polski rynek łatwiej accepuje niż US) |
| Pierwszy DM reply rate | 8-15% | 15-25% | 25%+ |
| InMail reply rate | 8-15% | 15-25% | 25%+ |
| Profile view → connection | 30%+ | 40%+ | 50%+ |
| Rozmowa DM → spotkanie | 15-25% | 25-35% | 35%+ |
Polski B2B SaaS ma wyższe accept rate niż US bo: mniej spam outreach, bardziej "polecamy się" kultura, mniej seniors zalanych wiadomościami. Ale niższy reply rate na zimne bo: kultura unikania konfrontacji, wolą nie odpowiadać niż odmówić.
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 · 274 lines · 175 tokens per session scan A 531257eabdc9
craig-linkedin-outreach-pl is a skill published in the GitHub repository DariuszCiesielski/polish-agent-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 175 tokens to every session and 4,163 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.