React Starter Kit is a full-stack monorepo template for building SaaS web applications with React, TypeScript, tRPC, and Cloudflare Workers. A monorepo keeps related applications and packages in one repository, while the template provides frontend, backend, authentication, billing, database, and development-tool foundations. The catalogue instructions, skills, and command help developers work with this starter kit.
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/kriasoft/react-starter-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/kriasoft/react-starter-kit/validate-auth-schema)<a href="https://agentmods.dev/commands/kriasoft/react-starter-kit/validate-auth-schema"><img src="https://agentmods.dev/badge/commands/kriasoft/react-starter-kit/validate-auth-schema/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/kriasoft/react-starter-kit/validate-auth-schema"><img src="https://agentmods.dev/badge/commands/kriasoft/react-starter-kit/validate-auth-schema.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 | $0.00000 | $0.00470 |
| Opus 5.5 | $0.00000 | $0.00188 |
| Sonnet 5.5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
validate-auth-schema 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.
What it actually says
Validate Auth Schema
Check that the Drizzle schema in db/schema/ still satisfies what Better Auth expects. Better Auth derives its required tables from the enabled plugins, so the generated JSON — not the upstream docs — is the source of truth:
bun run db/scripts/generate-auth-schema.ts
The script builds a real auth instance from apps/api/lib/auth.ts with fixed placeholder credentials, every optional integration switched on, so the output is the full set of tables rather than the subset your environment happens to enable. Per field it carries the type, the required, unique and index flags, any literal defaultValue, and the reference target with its onDelete. Per table it carries indexes: the composite indexes a plugin declares.
Compare that output against db/schema/ and report:
- Tables Better Auth expects that are missing, and tables no plugin in
auth.tsneeds any more. - Field-level drift: missing or extra columns, mismatched types, and
requiredoruniqueflags that disagree. - Foreign keys pointing at the wrong table or column.
- A
trueindexflag, a table-level entry inindexes, a literaldefaultValue, or anonDeletein the output is Better Auth asking for it: report a schema that lacks one. Indexes, defaults and cascades the project adds beyond that list are its own decisions — check those against the conventions indb/AGENTS.mdand do not report them as drift. - Local naming that must stay mapped, not renamed away: Better Auth's
accountis ouridentitytable. - Project-specific columns, indexes, and constraints are expected and fine on their own. Flag any that constrain a write Better Auth performs: a
NOT NULLcolumn with no database default breaks every insert into that table, and an extra unique or check constraint can reject a row Better Auth considers valid. Fields that must participate in its models belong inadditionalFieldsrather than added to the table behind its back.
Report findings with the specific fix for each. Do not run db:push, db:generate, or db:migrate as part of a validation — schema changes are a separate, deliberate step.
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 ce13130ed215
- 1mo ago First seen · 21 lines · 0 tokens per session scan A 2d19e2fb5777
validate-auth-schema is a command published in the GitHub repository kriasoft/react-starter-kit (23,693 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 470 tokens. 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.