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 tomzx/agents --skill create-projectgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/create-project)<a href="https://agentmods.dev/skills/tomzx/agents/create-project"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-project/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/tomzx/agents/create-project"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-project.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 | $0.00073 | $0.01789 |
| Opus 5.5 | $0.00029 | $0.00716 |
| Sonnet 5.5 | $0.00015 | $0.00358 |
| Haiku 4.5 | $0.00007 | $0.00179 |
Grade A, and why
create-project 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 15d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Project
Populates the project context files under .sdlc/context/ by interviewing the user, so a new or empty project has full context before any feature work starts.
initialize-sdlc-directory creates the context files as stubs, and sync-sdlc fills them by analyzing existing code.
An empty project has no code to analyze, which leaves stubs.
This skill closes that gap: it asks, one topic per round, the questions the stubs need answered, and writes each file as its round completes.
goals.md is deliberately out of scope: /create-goals owns it (see Next Step).
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md. - Optional project root (
$1); defaults to the current working directory. - The user is available to answer questions (this skill is interactive; never invent answers).
Steps
-
If the project root already contains source code (not just scaffolding like
.git/or a README), ask the user whether/sync-sdlcis the better tool, since code analysis produces more accurate context than an interview. Proceed only if the user confirms. -
If
.sdlc/does not exist at the project root, load and runinitialize-sdlc-directorywith$1first, per the Skill Handoff rule in shared.md, then continue here. -
Read every existing file under
.sdlc/context/. Sections that are already filled in count as answered; only ask about what is missing or still a placeholder. -
If
.sdlc/context/review-project.mdexists withverdict: changes-requested, operate in Revision Mode (below) instead of running the full interview. -
Run one interview round per topic, in this order. Each round presents four to six numbered questions about that topic only, then waits for the answers. The user may skip any question.
Round File Ask about 1 project-overview.mdWhat the project does and the problem it solves, key stakeholders, in-scope and out-of-scope capabilities, hard constraints (technical, business, regulatory) 2 use-cases.mdThe actors who use the project, the goals each one pursues with it (why they reach for it, not what its commands do), which goals exist today versus are wanted (with a signal for each wanted one), and what is deliberately out of scope 3 architecture.mdMajor components and their responsibilities, how data flows between them, core domain entities and their relationships, intended topology. For an empty project, capture the intended architecture and mark it as planned 4 infrastructure.mdLanguage, runtime, framework, and database choices, development tooling and its exact commands, environments, CI/CD pipelines, deployment and rollback 5 conventions.mdNaming (files, functions, classes), directory structure, coding standards, commit message format, branching strategy, how SDLC artifacts should be written 6 vocabulary.mdDomain terms the project will use, technical terms, acronyms and abbreviations
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.
- 15d ago Changed · +3 lines 0dc75394f9a6
- 22d ago Changed · +6 lines f4aeb524a396
- 23d ago Changed · -4 lines 31819feb0ccd
- 2mo ago First seen · 135 lines · 73 tokens per session scan A c56d72b85524
create-project is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 1,789 once invoked, about $0.0003 per session on Opus 5.5. 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…