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 aka-kika/akakika-skills --skill new-project-gategit clone --depth 1 https://github.com/aka-kika/akakika-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/aka-kika/akakika-skills/new-project-gate)<a href="https://agentmods.dev/skills/aka-kika/akakika-skills/new-project-gate"><img src="https://agentmods.dev/badge/skills/aka-kika/akakika-skills/new-project-gate/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/aka-kika/akakika-skills/new-project-gate"><img src="https://agentmods.dev/badge/skills/aka-kika/akakika-skills/new-project-gate.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 | $0.00159 | $0.01709 |
| Opus 5 | $0.00079 | $0.00855 |
| Sonnet 5 | $0.00032 | $0.00342 |
| Haiku 4.5 | $0.00016 | $0.00171 |
Grade A, and why
new-project-gate 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Project Gate
A gate, not a form. Run it before the editor opens.
The job is to kill bad ideas cheaply and let good ones through with their smallest proving cut already named. The failure mode this guards against is sprawl — fast at building the wrong thing is just faster sprawl.
After a project is built and shipped, run it through old-project-audit on the next pass to decide if it earned its keep.
Verdict at a glance
Checkpoint 0 or 1 → KILL |
Any other [ ] → CUT |
All green or [~] → GO |
|---|---|---|
| Tool shouldn't exist at all | Build smaller, fix the gap first | Build the dumbest proving cut |
[x] = passed · [ ] = failed · [~] = unsure / needs the human
How to run it
Walk the six checkpoints in order. For each one:
- Concise why — one line on what this checkpoint protects against.
- 1-2 line answer — verdict for this idea, holding both lenses. If the lenses disagree, say so; that disagreement is the signal.
- Mark the check —
[x][ ]or[~].
Stop early if checkpoint 0 or 1 fails hard. No point pricing the build of a tool that shouldn't exist.
The checkpoints
0. Deserves to exist as its own tool Standalone thing, or a feature of something already running? Overlap with the catalogue? Is a new surface justified?
- Agent lens: can an agent already reach this through an existing tool or MCP?
- Human lens: do I want a separate thing to open and maintain?
1. Real problem Whose problem, how often, what's done today instead?
- Agent lens: is there a task an agent repeatedly fails at without this, and how often does it come up?
- Human lens: do I hit this daily and suffer; would I reach for it unprompted next week?
2. Dumbest version that proves it Smallest cut that validates. File-first, no agent layer yet. Ugly is fine.
- Agent lens: minimum structured surface (files + schema) to drive it.
- Human lens: minimum UI I'd actually touch within a week.
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 · 136 lines · 159 tokens per session scan A 4733b66505fc
new-project-gate is a skill published in the GitHub repository aka-kika/akakika-skills (10 stars, last pushed 2d ago), licensed MIT. It adds 159 tokens to every session and 1,709 once invoked, about $0.0008 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
apple-design
Cross-platform UI/UX design reviewer grounded in Apple's Human Interface Guidelines (122 pages pulled from developer.apple.com, including 57 component pages) plus a design-craft lens for distinctive, non-templated work. Use it to audit, review, critique, or improve any mobile app (iOS, Flutter, React Native) or…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…