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 dealing-with-reportersgit 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/dealing-with-reporters)<a href="https://agentmods.dev/skills/kalyvask/winning-writing/dealing-with-reporters"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/dealing-with-reporters/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/dealing-with-reporters"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/dealing-with-reporters.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 90 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00158 | $0.02818 |
| Opus 5 | $0.00079 | $0.01409 |
| Sonnet 5 | $0.00032 | $0.00564 |
| Haiku 4.5 | $0.00016 | $0.00282 |
Grade A, and why
dealing-with-reporters 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dealing with reporters
Source: Andrew Ross Sorkin (NYT DealBook / Squawk Box) and Glenn Kramon's Winning Writing class lecture on press relations. AP attribution definitions baked in.
Why this skill exists
Most executives wing it with reporters and then spend the next decade in litigation. The 11 rules below come from Sorkin, who has interviewed CEOs through every flavor of crisis since 2007, plus Kramon's three decades editing the New York Times business section. The rules are battle-tested. The tradeoffs are real.
Sorkin's 11 rules
1. Never say "no comment"
There's always something better, even if you can't say much. "I'd love to be able to walk you through this, but the investigation is still active and law enforcement has asked us not to discuss specifics yet" beats "no comment" every time. The first sentence is a quote the reporter can use without making you look evasive. The second is the actual reason.
2. Don't avoid calls
Bad feelings compound. You lose the chance to understand what the reporter is actually after, and you lose the chance to shape your side of the story. Even if you're not ready to comment, take the call and say so.
3. Know the journalist
Read their last six pieces before talking to them. Talk to peers they've quoted. Some are more trustworthy than others. You won't always have a choice — but knowing who you're dealing with changes what you say and how.
4. Build relationships before you need them
The reporter who knows your business in depth will write a more nuanced story when something goes wrong. That doesn't mean they'll be soft. It means they'll be accurate. Build the relationship in good times.
5. Address the question, tell the truth, hedge when you must
Say as much as you can confidently say. If you don't know, say so. Don't overpromise: "It won't happen again" and "We assure you our system is safe" are statements that age badly. "Based on what we know today" is the right frame.
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 · 187 lines · 158 tokens per session scan A 395926e14947
dealing-with-reporters is a skill published in the GitHub repository kalyvask/winning-writing (14 stars, last pushed 6d ago), licensed MIT. It adds 158 tokens to every session and 2,818 once invoked, about $0.0008 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
012-agile-epic
Guides the creation of agile epics with comprehensive definition including business value, success criteria, and breakdown into user stories. Use when the user wants to create an agile epic, define large bodies of work, break down features into user stories, or document strategic initiatives. This should trigger for…
005-agents-installation
Use when you need to install the embedded robot agents into .github/agents, .claude/agents, .cursor/agents, or .codex/agents, selecting the destination interactively and copying the embedded agent definitions from project assets. This should trigger for requests such as Install embedded agents; Bootstrap…
004-commands-installation
Use when you need to install the embedded project commands into command directories (.github/commands, .claude/commands, .cursor/command, .codex/commands), selecting the destination interactively and copying the embedded command definitions from project assets. This should trigger for requests such as Install embedded…
agent-ready-x402
Sub-skill de agent-ready-cloudflare: Implement x402 Payment Protocol.
web3-protocol-gtm
Go-to-market strategy for web3 builders - protocols, products, services, and solo founders. Use when planning growth for a crypto protocol, building developer community, crafting CT narrative, planning ecosystem partnerships, preparing grant applications, launching tokens, pricing crypto-native products, or growing as…
x402
Build internet-native payments with x402 - HTTP 402 for on-chain micropayments, no accounts or API keys. Use for paid APIs, paywalled content, agent payment flows, or per-call MCP tools. TypeScript, Python, and Go SDKs across EVM and Solana.