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 2ykwang/agent-skills --skill worth-buildinggit clone --depth 1 https://github.com/2ykwang/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/2ykwang/agent-skills/worth-building)<a href="https://agentmods.dev/skills/2ykwang/agent-skills/worth-building"><img src="https://agentmods.dev/badge/skills/2ykwang/agent-skills/worth-building/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/2ykwang/agent-skills/worth-building"><img src="https://agentmods.dev/badge/skills/2ykwang/agent-skills/worth-building.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 | $0.00128 | $0.02150 |
| Opus 5 | $0.00064 | $0.01075 |
| Sonnet 5 | $0.00026 | $0.00430 |
| Haiku 4.5 | $0.00013 | $0.00215 |
Grade A, and why
worth-building 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
worth-building
Pick the right level of elaboration for what the user wants to build, then return a concrete proposal for how to solve it at that level. Use it for build decisions broadly — scripts, features, systems, docs, automation. Not limited to software.
The output is a proposal, not a verdict. "Level 2 of 3" is useless to anyone. What's useful: "build it in this shape, this was deliberately left out, raise it when you see this signal."
Input comes from $ARGUMENTS when invoked explicitly, or from the surrounding conversation.
One principle
Default to the lowest rung that holds. You don't prepare for complexity up front — you earn your way up to it.
This is the default, not one option among many, because the cost is asymmetric. Going simple→robust later is cheap: you bolt it on. Going robust→simple is expensive: you rip it out, you don't get the time back (sunk cost), and you discover the code was overfit to requirements that never arrived. When in doubt, the lower rung is the cheaper mistake.
Complexity earns a rung up only two ways: earned (the simple version measurably falls short) or forced (a hard constraint makes low investment irresponsible). Forcing constraints are non-negotiable and never "right-sized" away: input validation at trust boundaries, error handling that prevents data loss, security, accessibility basics, and anything the user explicitly asked for.
Steps
1. Understand the problem; ask to fill what's missing
Extract from the request and its context:
- who it's for, what problem it solves
- what "done / works" actually means here
- hard constraints (deadline, existing stack, security/data/compliance boundaries)
- how reversible this decision is, and how bad it is if wrong
Find the design-splitting pivots first. Name the 2-3 domain-specific facts where a different answer flips the whole technical direction (for payments: does the PSP support idempotency; for a calendar digest: shared calendar or personal aggregation). Generic axes (stakes, reversibility) only rank candidates — the pivots decide what the candidates even are. The skill can't list domain pivots for you. You find them with domain knowledge on every request.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 119 lines · 128 tokens per session scan A 76a3b8f1d6b3
worth-building is a skill published in the GitHub repository 2ykwang/agent-skills (18 stars, last pushed 1mo ago), licensed MIT. It adds 128 tokens to every session and 2,150 once invoked, about $0.0006 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
resolve-plugins
Curate Claude Code skill / MCP / hook picks against live upstream sources and pin them in .claude/settings.json. Adding a process harness (a paired skill set) is an ordinary pick this door handles. Reads stack from docs/techstack.md, workflow signal from docs/overview.md + existing pins, then live-queries six source…
dev-environment-bootstrapping
Use this skill when the user asks to bootstrap, set up, create, or initialize a Shopware development environment from scratch — phrases like "set up a Shopware dev environment", "clone and install Shopware", "initialize a Shopware plugin project", "bootstrap Shopware and a new plugin called X", "get a fresh Shopware…
phpunit-integration-to-unit-migrating
Use this skill ONLY when the user explicitly requests an audit, migration, or evaluation of whether a Shopware integration test belongs in the unit suite — trigger phrases like "audit integration tests", "migrate integration tests to unit", "is this an integration test or a unit test", "evaluate integration tests for…
commit-message-writing
Use this skill when the user explicitly asks to generate, write, draft, or create a commit message, squash commit, commit title, or merge commit message for the Shopware core repository (shopware/shopware). Supports two modes — full commit messages (title + body) for branch commits, and squash merge titles…
hermes-diagnostic-review
Use when running a read-only diagnostic review of recent Hermes sessions to find recurring mistakes, failed tool calls, and repeated fixes, then propose suggestion-only improvements and reusable skills. Human-gated; never auto-applies.
pr-description-writing
Use this skill when the user asks to write, draft, create, or improve a PR description, is about to create a PR, or mentions "PR description", "pull request description", or "PR template" — AND that PR targets trunk in the Shopware core repository (shopware/shopware). The skill detects the target and only activates…