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 DamiMartinez/book-skills --skill hard-thing-about-hard-thingsgit clone --depth 1 https://github.com/DamiMartinez/book-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/damimartinez/book-skills/hard-thing-about-hard-things)<a href="https://agentmods.dev/skills/damimartinez/book-skills/hard-thing-about-hard-things"><img src="https://agentmods.dev/badge/skills/damimartinez/book-skills/hard-thing-about-hard-things/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/damimartinez/book-skills/hard-thing-about-hard-things"><img src="https://agentmods.dev/badge/skills/damimartinez/book-skills/hard-thing-about-hard-things.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 | $0.00203 | $0.01299 |
| Opus 5 | $0.00102 | $0.00649 |
| Sonnet 5 | $0.00041 | $0.00260 |
| Haiku 4.5 | $0.00020 | $0.00130 |
Grade A, and why
hard-thing-about-hard-things 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 11d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Hard Thing About Hard Things
Apply this skill to CEO/leadership problems that don't have a clean textbook answer — Horowitz's core claim is that most management books cover how to do things right, but the hard part of running a company is what to do when there's no good option, only less-bad ones.
Core concepts
The Struggle — The psychological state of grinding through a period where the company/situation might genuinely fail and there's no clear playbook. The right response isn't to pretend there's a clean answer; it's to keep making the best decision available with incomplete information, separate the decision from the emotion, and keep moving. When a user describes a situation with no good options, name that explicitly instead of forcing a false "best practice."
Wartime vs. peacetime CEO/manager — Peacetime: focus on process, broad initiatives, expanding the market, tolerating some deviation from plan. Wartime: survival is on the line — tight execution focus, less tolerance for competing priorities or politics, faster and more centralized decisions. Neither mode is "correct" universally; the right one depends on whether the org's existence is currently at stake. Diagnose which mode a situation actually calls for before recommending a management style.
No easy answers, only hard choices — When a decision has real costs on every branch (e.g. layoffs, killing a product line, demoting a friend), don't search for a way to avoid the tradeoff — name the tradeoff, pick a side deliberately, and own the consequence. Resist the urge to soften hard decisions into ambiguity, which usually makes the outcome worse for everyone involved.
Take care of the people, the products, and the profits — in that order — When resources/attention are scarce, sequence matters: treat people (especially those affected by hard decisions) with respect and honesty first, then get the product right, then the business results follow. Useful lens when a user is deciding how to sequence a hard announcement or a turnaround.
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.
- 11d ago First seen · 42 lines · 203 tokens per session scan A 23c14dc5bf4c
hard-thing-about-hard-things is a skill published in the GitHub repository DamiMartinez/book-skills (11 stars, last pushed 1mo ago), licensed MIT. It adds 203 tokens to every session and 1,299 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…