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/solanabr/solana-ai-kitWrote 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/solanabr/solana-ai-kit/build-app)<a href="https://agentmods.dev/commands/solanabr/solana-ai-kit/build-app"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/build-app/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/solanabr/solana-ai-kit/build-app"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/build-app.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 | $0.00020 | $0.00598 |
| Opus 5.5 | $0.00008 | $0.00239 |
| Sonnet 5.5 | $0.00004 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
build-app 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build the web client in $ARGUMENTS (default: the app directory whose package.json has a build script) for the cluster its program is deployed on. Current client patterns: frontend.md.
Steps
- Install with the package manager that owns the lockfile (
pnpm-lock.yaml,yarn.lock,bun.lock/bun.lockb,package-lock.json), in frozen mode (npm ci,pnpm install --frozen-lockfile). - Env: if
.env.localis missing, copy it from.env.examplewithout overwriting anything. Check that the program ID and RPC URL match the target cluster (compare with.program-id-devnet/.program-id-mainnetwritten by/deploy). If the program interface changed, regenerate the client first with/generate-idl-client. - Type-check with
tsc --noEmit: Vite builds do not type-check,next builddoes. Run thelintscript if there is one. - Build with
<pm> run build. Output:.next/(Next.js),dist/(Vite),build/(CRA). - Verify: no
*.mapfiles in the production output unless intended; note the largest JS chunks; preview with<pm> run start(Next.js) or<pm> run preview(Vite).
Failure fixes
Buffer is not defined(Vite): addvite-plugin-node-polyfillswithnodePolyfills({ include: ['buffer'] }). web3.js 1.x, the Anchor TS client (@anchor-lang/core) and wallet-adapter need it;@solana/kitdoes not.window is not definedor hydration errors (Next.js): wallet and web3 code belongs in'use client'leaf components.- Env var undefined in the browser: client-side vars need the
NEXT_PUBLIC_orVITE_prefix, and a rebuild, because they are inlined at build time. - Oversized bundle: lazy-load wallet UI and heavy SDKs; drop
@solana/wallet-adapter-walletsbundles, since Wallet Standard wallets register themselves; prefer@solana/kitover web3.js 1.x for new code.
Guardrails
- Every
NEXT_PUBLIC_/VITE_value ships in the bundle. Keep RPC URLs that embed an API key (Helius and similar) behind a server route.
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 Changed · -305 lines · +7 tokens per session scan C → A b3a9e1c1060f
- 1mo ago Changed da421faf3192
- 1mo ago First seen · 334 lines · 13 tokens per session scan C e4f2f0bd6940
build-app is a command published in the GitHub repository solanabr/solana-ai-kit (104 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 598 once invoked, about $0.0001 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 commands, from other repositories
apex
APEX Methodology - The systematic Analyze-Plan-Execute-eLicit-eXamine approach for intelligent development. Reduces hallucination and defect risk through mandatory parallel research, self-review, and validation gates.
explain-architecture
Analyze and explain software architecture with ASCII diagrams and pattern detection. Creates visual representations of system design.
prompt
Create or optimize prompts using best practices.
design-audit
Audit an existing HTML/CSS design. Deterministic checks only (contrast, fonts, colors, states, dark mode) plus a visual pass. No generation.
fix-pr-comments
Systematically resolve Pull Request review comments using gh CLI to fetch comments and apply requested changes.
watch
Check for Claude Code updates, detect breaking changes, analyze plugin compatibility, and optionally gather community pulse via Exa.