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 ohong/agent-skills --skill name-itgit clone --depth 1 https://github.com/ohong/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/ohong/agent-skills/name-it)<a href="https://agentmods.dev/skills/ohong/agent-skills/name-it"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/name-it.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.01972 |
| Opus 5 | $0.00014 | $0.00986 |
| Sonnet 5 | $0.00006 | $0.00394 |
| Haiku 4.5 | $0.00003 | $0.00197 |
Grade A, and why
name-it 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 8d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name It
Naming is positioning, not labeling. You aren't choosing a word — you're compressing a brand's story, feeling, and promise into one, and a name is the first thing anyone encounters: it buys credibility up front or bleeds it before it's earned. This skill distills Willem Van Lancker's How to Name Anything in an Afternoon (bundled, with page pointers), plus the field wisdom of David Placek (Lexicon Branding — BlackBerry, Pentium, Azure, Sonos, Vercel) and A Hundred Monkeys.
How to navigate this skill
Read this file fully — it is the method. Pull in reference material only when you reach the phase that needs it:
| Load | When | Contains |
|---|---|---|
references/generation.md |
Starting Exploration (Phase 2) | 9 generation techniques, name-type taxonomy with examples, feelings palette, suffix lists |
references/evaluation.md |
Starting Distillation/Validation (Phases 3–4) | Six dimensions, Memory/Meaning/Range scoring, sound symbolism, phonetics checks, human-testing protocols |
references/finalization.md |
Diligence on finalists through post-decision (Phases 4.3–6) | Trademark, domain strategy, mockups, decision methods, lock-in, regret handling, stewardship |
references/masters.md |
Process stalls on human factors, or you need a doctrinal tiebreaker | Objection-handling table, the three schools, Placek's Diamond |
references/naming-guide.pdf |
You need the author's full treatment of a section | Full 40-page guide. Cite as §section + PDF page. Printed footer numbers run one behind (footer 19 = PDF p. 20); table of contents on PDF p. 6 |
First principles
- Orient before generating — always. Never produce names before knowing, at minimum: what it does, who it's for, and the one feeling it should evoke. Even when the user says "just give me names," ask those three questions first; 60 seconds of orientation transforms output quality.
- Volume before judgment. Great names come from candidate #700, not #7. Generate wide (Lexicon runs 1,000–1,500), evaluate only afterward — premature judgment kills originality.
- Comfort is a warning sign. Distinctive names feel uncomfortable at first (Azure was "dumb," BlackBerry "crazy"). Polarization signals energy; universal mild approval signals forgettable.
- No eureka. Nobody "knows it when they see it" — across thousands of professional projects the aha moment essentially never comes. Score against criteria instead of waiting for goosebumps.
- 2 of 3 on Memory / Meaning / Range = viable. 3 of 3 is rare magic; 0–1 gets cut.
- A name starts a conversation. It doesn't need to explain the business; it needs to earn the question that lets the story be told. Needing a story is good; needing an apology is not.
- Never let domain availability choose the name. The .com is an area code, not the address — modifiers and alt TLDs unlock almost any name.
- Crowds inform, one person decides. Groups agree on what's easy to agree on. Structured testing feeds a single decision-maker; committees find the safe middle.
- Sound carries meaning before semantics. Letters have psychological vibrations (B = reliable, V = alive, Z = fast) — use phonetics as a design material, not an afterthought.
- The name is 20%; stewardship is 80%. Names accrue meaning through consistent, confident use — they don't start with it. There is no perfect name, only a name used with conviction.
What ships with it
6 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.
- 8d ago First seen · 85 lines · 28 tokens per session scan A 8b8d76ef6eaa
name-it is a skill published in the GitHub repository ohong/agent-skills (3 stars, last pushed 8d ago), licensed MIT. It adds 28 tokens to every session and 1,972 once invoked, about $0.0001 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
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…