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 agentmods add skills/narpatsinghpurohit/tstack/generating-react-featuresnpx skills add narpatsinghpurohit/tstack --skill generating-react-featuresgit clone --depth 1 https://github.com/narpatsinghpurohit/tstackWhat 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 | $0.00057 | $0.00874 |
| Opus 5 | $0.00028 | $0.00437 |
| Sonnet 5 | $0.00011 | $0.00175 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
generating-react-features 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 2d 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.
Live Context
- Existing features: !
ls apps/web/src/features/ - Existing routes: !
ls apps/web/src/routes/_authenticated/ 2>/dev/null - Shared schemas: !
ls packages/shared/src/schemas/ 2>/dev/null || ls shared/src/schemas/ 2>/dev/null || echo "check shared/"
Task
Create feature: $ARGUMENTS
Generating React Features
The Pattern
Every feature uses exactly 3 files + index. No exceptions.
features/<domain>-<action>/
├── <domain>-<action>.hook.ts # Business logic (custom hook)
├── <domain>-<action>.view.tsx # Pure UI (props only, ZERO hooks)
├── <domain>-<action>.tsx # Glue: calls hook, renders view
├── index.ts # Public API
├── _components/ # Private sub-components (CAN use hooks)
└── _hooks/ # Private helper hooks
Rules (non-negotiable)
- View files contain ZERO hooks. No useState, useEffect, useQuery, useCan, useNavigate. Nothing.
- Hook return type === View props type. TypeScript-enforced contract.
- Glue file is a one-liner.
<View {...useHook()} />. No logic. - Features are flat directories.
features/course-list/, NOTfeatures/admin/course/. - Domain prefix groups related features.
course-list/,course-detail/,course-editor/. - No cross-feature imports.
features/Xcannot import fromfeatures/Y. - API hooks live in the feature. Promote to
shared/api/queries/only when a second consumer appears.
Workflow
- [ ] Step 1: Create feature directory
- [ ] Step 2: Define ViewProps type
- [ ] Step 3: Create API hooks (query key factory)
- [ ] Step 4: Create feature hook (returns ViewProps)
- [ ] Step 5: Create pure view (accepts ViewProps, ZERO hooks)
- [ ] Step 6: Create glue file (one-liner)
- [ ] Step 7: Create index.ts
- [ ] Step 8: Create route (thin wrapper)
- [ ] Step 9: Add _components/ if needed
- [ ] Step 10: Add _hooks/ if needed
Conventions
- Named exports for all components
- Ternary for conditional rendering, not
&& import typefor type-only imports- Forms:
react-hook-form+zodResolverwith schemas from the shared package - Dark mode: semantic Tailwind classes (
bg-background,text-foreground) - Response envelope: access via
r.data.data - Package manager: bun (NEVER npm/npx)
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.
- 2d ago First seen · 85 lines · 57 tokens per session scan A d76028698761
generating-react-features is a skill published in the GitHub repository narpatsinghpurohit/tstack (5 stars, last pushed 5mo ago), licensed MIT. It adds 57 tokens to every session and 874 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
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
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…