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 kalyvask/winning-writing --skill recipient-researchgit clone --depth 1 https://github.com/kalyvask/winning-writingWrote 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/kalyvask/winning-writing/recipient-research)<a href="https://agentmods.dev/skills/kalyvask/winning-writing/recipient-research"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/recipient-research/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/kalyvask/winning-writing/recipient-research"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/recipient-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00107 | $0.01134 |
| Opus 5 | $0.00053 | $0.00567 |
| Sonnet 5 | $0.00021 | $0.00227 |
| Haiku 4.5 | $0.00011 | $0.00113 |
Grade A, and why
recipient-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 10d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recipient research
Source: points/cold-email-rules.md (rule 1 — know something about the person and exploit it).
Why this exists
Konrad's first rule of cold outreach: research is non-negotiable. People drop personal details in 20-minute podcast interviews. Recent blog posts. Portfolio company pages. Conference talks. The specificity is what separates a real email from a template.
You have 15 seconds when the recipient opens your email. Three concrete personal details earn those 15 seconds. A LinkedIn summary doesn't.
What to find
For every cold-email target, build a dossier with these sections:
1. Public role and trajectory
- Current title and company
- Last 2–3 roles and how long they stayed (signals: founder vs. operator, builder vs. acquirer)
- The pivot points — what made them leave each role, what made them join the next
- Anything they've publicly said about why they're at the current job
2. Public writing and speaking
- Substack, Medium, personal blog, company blog
- Podcasts they've appeared on (especially long-form — 60+ minutes)
- Conference talks on YouTube
- Twitter/X — pinned tweets, recent threads
- LinkedIn posts (ignore the corporate ones; surface the personal ones)
- Books they've recommended or written
3. Distinctive personal details
This is the gold. Pull anything that is:
- A specific anecdote they've told publicly (the year, the place, the name)
- An unusual hobby (Ironman, jiu-jitsu, beekeeping, jazz piano)
- A geographic origin or move (immigrated from X, grew up in Y)
- A formative experience (military service, an early failure, a mentor)
- A strong opinion (especially one that's contrarian or unexpected)
- A specific number they've cited about their work
4. Their current focus / what they're hunting for
- If a VC: their portfolio, their public thesis, what they've said they want to fund
- If a CEO: hiring posts, their company's strategic moves, recent product launches
- If a hiring manager: open roles on their team, public posts about culture or hiring bar
- If a journalist: their last 5 stories, what they're sourcing for next
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.
- 10d ago First seen · 116 lines · 107 tokens per session scan A 798532d9433d
recipient-research is a skill published in the GitHub repository kalyvask/winning-writing (13 stars, last pushed 4d ago), licensed MIT. It adds 107 tokens to every session and 1,134 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
project-memory
Generate a project-specific context file from a brief so an AI assistant remembers your editorial constraints, voice, audience, and quality bar across sessions.
project-retrospective
Generate a LESSONS.md from a finished project: what worked, what didn't, what to reuse, what to retire — formatted for next-project carry-over.
template-selector
Recommend the right skill bundle, agent, and workflow sequence for a new project — so media professionals can start producing instead of browsing a 394-skill library.
jargon-flagger
Scans a draft and flags every instance of technical jargon, unexplained acronyms, and insider language that a general-audience reader would not understand — with a plain-language alternative for each.
multi-author-harmonizer
Reviews a text written or assembled by multiple authors and produces a detailed inconsistency report — flagging voice shifts, terminology mismatches, tonal clashes, and formatting discrepancies — with specific harmonisation recommendations for each.
passive-voice-checker
Identifies every passive-voice construction in a draft, assesses whether each weakens or serves the prose, and offers active-voice alternatives for those that should be changed — while leaving justified passives alone.