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 T4LEL/Claude-Arsenal --skill new-projectgit clone --depth 1 https://github.com/T4LEL/Claude-ArsenalWrote 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/t4lel/claude-arsenal/new-project)<a href="https://agentmods.dev/skills/t4lel/claude-arsenal/new-project"><img src="https://agentmods.dev/badge/skills/t4lel/claude-arsenal/new-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/t4lel/claude-arsenal/new-project"><img src="https://agentmods.dev/badge/skills/t4lel/claude-arsenal/new-project.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 | $0.00061 | $0.01076 |
| Opus 5 | $0.00030 | $0.00538 |
| Sonnet 5 | $0.00012 | $0.00215 |
| Haiku 4.5 | $0.00006 | $0.00108 |
Grade A, and why
new-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 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Project
Take a raw idea to a running, git-tracked, Claude-ready project skeleton.
Templates are bundled with this skill in templates/ (synced copies — the source of truth is the toolkit repo at X:\Projects\ClaudeCode\templates\; edit there, then re-run sync.ps1).
Copy this checklist and check off items as you complete them:
New Project Progress:
- [ ] Step 1: Gather requirements
- [ ] Step 2: Design gate
- [ ] Step 3: Scaffold by type
- [ ] Step 4: CLAUDE.md + git init
- [ ] Step 5: Verify it runs (mandatory)
- [ ] Step 6: Hand off
Step 1 — Gather
Use what the user already provided (including arguments to this skill); ask only for what's missing.
- Name (kebab-case) and one-line purpose.
- Type: webapp (default), api, or other.
- Location: default
X:\Projects\<name>. - Paid product? If yes, note it — Step 6 points at
/monetize.
Step 2 — Design gate
If the product hasn't been brainstormed yet in this conversation, invoke superpowers:brainstorming for the product itself BEFORE scaffolding. Never scaffold an undesigned product. If a design/spec already exists, proceed.
Step 3 — Scaffold by type
If a scaffold command fails, stop and fix it before continuing: read the exact error; for generator flag errors run the generator's --help and adapt — flags drift between versions and the intent below matters more than the exact flags. Never leave a half-scaffolded folder silently: finish it, or delete it and report why.
webapp (Next.js + TypeScript + Tailwind + Supabase):
npx create-next-app@latest <name> --typescript --tailwind --eslint --app --src-dir --import-alias "@/*" --use-npm --yes
cd <name>
npm install @supabase/supabase-js @supabase/ssr
Then create .env.example (NEXT_PUBLIC_SUPABASE_URL, NEXT_PUBLIC_SUPABASE_ANON_KEY, commented), src/lib/supabase/ client helpers per current @supabase/ssr docs (fetch them via the context7 MCP tools — the cookie/session patterns change), and a supabase/migrations/ folder. Only create the actual Supabase project when the design needs a database — ask before creating cloud resources.
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 · 80 lines · 61 tokens per session scan A 97303916af1e
new-project is a skill published in the GitHub repository T4LEL/Claude-Arsenal (1 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 1,076 once invoked, about $0.0003 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
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
annotating-task-lineage
Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
checking-freshness
Quick data freshness check. Use when the user asks if data is up to date, when a table was last updated, if data is stale, or needs to verify data currency before using it.