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 bartstc/vite-ts-react-template --skill building-blocksgit clone --depth 1 https://github.com/bartstc/vite-ts-react-templateWrote 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/bartstc/vite-ts-react-template/building-blocks)<a href="https://agentmods.dev/skills/bartstc/vite-ts-react-template/building-blocks"><img src="https://agentmods.dev/badge/skills/bartstc/vite-ts-react-template/building-blocks/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/bartstc/vite-ts-react-template/building-blocks"><img src="https://agentmods.dev/badge/skills/bartstc/vite-ts-react-template/building-blocks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 18 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 31 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 41 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 55 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 70 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00074 | $0.01434 |
| Opus 5.5 | $0.00030 | $0.00574 |
| Sonnet 5.5 | $0.00015 | $0.00287 |
| Haiku 4.5 | $0.00007 | $0.00143 |
Grade A, and why
building-blocks 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 1mo 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.
Frontend Building Blocks
Typed catalog of building blocks used in this project. Each block has a fixed name, layer, composition rules, and canonical example.
How to Use
Read the rule file for each block you are about to implement. The summaries below are for routing — the rule files contain the full pattern.
Composition ladder
Composition is a ladder. Default to the bottom rung; climb only when a concrete, named pain appears. Each rung buys flexibility and costs indirection.
| Rung | Block | Reach for it when… |
|---|---|---|
| 1 | pure-component |
default — reusable UI is a function of its props. |
| 2 | compound-component |
a component grows a prop per shape, or callers need a layout the props did not anticipate. |
| 3 | composer |
one piece of UI must render data from swappable/deferred sources, or you want a fixture source for tests. |
| 4 | composer |
state must cross a component boundary (callbacks drilled to a leaf) and the layout should stay pure. |
Do not climb for uniformity, for a single source with no alternative in sight, or for state that never leaves its component.
Block Catalog
Data Fetching
| Block | Layer | Summary | File |
|---|---|---|---|
mutation-options-factory |
lib/api/ |
Reusable mutationOptions() factories with domain error translation. Composed by mutation-hook in providers/. |
rules/mutation-options-factory.md |
mutation-hook |
providers/ |
Server write via useMutation composed from mutation-options-factory, with cache invalidation. Returns [handler, isPending]. |
rules/mutation-hook.md |
query-options-factory |
lib/api/ |
Reusable queryOptions() factories — no hooks, no useQuery. Hook composition belongs in providers/. |
rules/query-options-factory.md |
query-keys-factory |
lib/api/ |
Hierarchical as const key tuples per resource. Single source of truth for cache invalidation. |
rules/query-keys-factory.md |
dto-model |
lib/api/ |
TypeScript interfaces mirroring the raw API wire format. No transformations. | rules/dto-model.md |
What ships with it
23 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.
- metadata.json 1.2 KB
- README.md 2.3 KB
- rules/composer.md 5.8 KB
- rules/compound-component.md 5.5 KB
- rules/dto-model.md 1.2 KB
- rules/error-boundary.md 1.1 KB
- rules/facade-hook.md 2.6 KB
- rules/form.md 4.5 KB
- rules/frontend-model.md 1.1 KB
- rules/hoc.md 1.5 KB
- rules/machine.md 8.8 KB
- rules/mutation-hook.md 1.7 KB
- rules/mutation-options-factory.md 2.5 KB
- rules/named-effect.md 1.2 KB
- rules/notification-hook.md 1.8 KB
- rules/page.md 1.8 KB
- rules/provider.md 2.7 KB
- rules/pure-component.md 1.5 KB
- rules/query-keys-factory.md 1.4 KB
- rules/query-options-factory.md 1.9 KB
- rules/store.md 1.2 KB
- rules/use-case-hook.md 2.3 KB
- rules/value-object.md 2.2 KB
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.
- 1mo ago First seen · 80 lines · 74 tokens per session scan A 1ee1e6393142
building-blocks is a skill published in the GitHub repository bartstc/vite-ts-react-template (124 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 1,434 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 2026-08-30.
Other skills, from other repositories
weapp-vite-react-best-practices
A Chinese-language guide for building React 19 WeChat mini programs with weapp-vite and @weapp-vite/react. WeChat mini programs are small apps that run inside WeChat.
typescript-react
Apply, review, and explain React conventions from the TypeScript Style Guide. Use automatically for TypeScript and TSX tasks involving prop-derived state, prop typing, component responsibilities, data flow, compound components, or client and server state.
git
A guide to common Git version-control workflows. Git records changes to code so developers can work in branches, combine changes, and review project history.
github
A guide to using GitHub CLI, a command-line tool for working with GitHub repositories. It covers issues, pull requests, releases, labels, milestones, and workflow runs.
storybook
A guide for writing Storybook stories, which are isolated examples used to develop and document interface components. It focuses on the current Component Story Format and reusable component inputs.
github-actions
A guide for creating and maintaining GitHub Actions workflows, which are automated jobs that run in a repository, such as tests or deployments. It also covers action versions and common security risks.