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.
git clone --depth 1 https://github.com/MohammadShehadeh/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/commands/mohammadshehadeh/agent-skills/new-feature)<a href="https://agentmods.dev/commands/mohammadshehadeh/agent-skills/new-feature"><img src="https://agentmods.dev/badge/commands/mohammadshehadeh/agent-skills/new-feature/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/commands/mohammadshehadeh/agent-skills/new-feature"><img src="https://agentmods.dev/badge/commands/mohammadshehadeh/agent-skills/new-feature.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 | $0.00038 | $0.01364 |
| Opus 5 | $0.00019 | $0.00682 |
| Sonnet 5 | $0.00008 | $0.00273 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade A, and why
new-feature 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 10d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build a new feature: $ARGUMENTS
Load the agent-skills-conventions skill. Work through the phases in order — phases 1–3 are the plan; no code before it's confirmed.
1. Understand — user journey & business logic
- Walk the user journey end to end, step by step: what the user sees, does, and expects at each point, including empty, loading, and failure states. A "Gmail-like inbox" becomes: scan list → open message → read → act (reply / archive / delete) → return to list.
- Extract the business logic from the journey: the rules and decisions behind each step (what marks a message read? who can archive? what sorts the list?). These are pure decisions — they'll live in
lib/, tested, separate from the UX flow that triggers them. - Restate both as verifiable targets: concrete behaviors, inputs/outputs, error cases with their
ErrorKeys — not vague ambitions. - Survey what exists: grep for similar features, reusable services/hooks/primitives. Extending beats duplicating; duplicating a small pure thing beats coupling to another feature's internals.
- State assumptions and ask about anything ambiguous — do not pick an interpretation and run.
2. Decompose the UI — atomic design, high level first
Once the journey is clear, the architecture falls out of it. Outline top-down, then build bottom-up:
- Pages — one per journey destination (
/inbox,/inbox/[messageId]), thin server components that only compose sections. - Blocks / sections — one per journey step or screen region (
MessageList,MessageToolbar,ThreadView,ComposePanel), each a single responsibility. - Primitives — existing shared UI first (
Button,Badge,Avatar,Field); a new primitive only when no shared one fits.
Keep the atomic layers flat in the tree: page → section → primitive, no pass-through wrappers. Name every unit by business meaning (MessageRow, not ListItem2), and list what data each one renders — content as typed as const arrays where it's static.
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.
- 10d ago First seen · 68 lines · 38 tokens per session scan A d6d40a8687d7
new-feature is a command published in the GitHub repository MohammadShehadeh/agent-skills (2 stars, last pushed 27d ago), licensed MIT. It adds 38 tokens to every session and 1,364 once invoked, about $0.0002 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 commands, from other repositories
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
design-form
Design a form with the fewest fields that works, clear labels, and errors that help.
frontend-3d
You are an expert in 3D web development using Three.js, React Three Fiber, WebGL, and WebGPU. You create immersive 3D experiences for the web.
frontend-design
Read and follow the instructions in agents/frontend-design/design-all.md. Also read all referenced files in agents/frontend-design/reference/ as needed for the task.
get-component-source
The full TSX source of a component (append " demo" for its usage example).