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 gaia-react/gaia --skill new-routegit clone --depth 1 https://github.com/gaia-react/gaiaWrote 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/gaia-react/gaia/new-route)<a href="https://agentmods.dev/skills/gaia-react/gaia/new-route"><img src="https://agentmods.dev/badge/skills/gaia-react/gaia/new-route/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/gaia-react/gaia/new-route"><img src="https://agentmods.dev/badge/skills/gaia-react/gaia/new-route.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 | $0.00087 | $0.00699 |
| Opus 5.5 | $0.00035 | $0.00280 |
| Sonnet 5.5 | $0.00017 | $0.00140 |
| Haiku 4.5 | $0.00009 | $0.00070 |
Grade A, and why
new-route 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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
new-route
Workflow
- Confirm with the user: the name (kebab-case) as free text, then the group (
_publicor_session), whether the page loads service data (and which variant), and whether it needs--action, as oneAskUserQuestioncall of three questions, each with its recommended answer first and marked(Recommended). Pass--i18nwhenever the project has i18n (app/i18n.tsexists): without it the page carries literal text, which lint (i18next/no-literal-string) rejects. - Run from the repo root:
./.gaia/cli/gaia scaffold route <name> --group <group> [flags](the package comes from the registry, not the working directory). Flags:./.gaia/cli/gaia scaffold route --help. - Verify:
pnpm typecheckclean;pnpm devreaches the new route. - Before filling in the page, loader, or action by hand, read one or two existing routes with a similar shape and follow their pattern.
The scaffold writes app/routes/<group>.<name>.tsx plus app/pages/<name>/page.tsx (export <Name>Page) with tests/page.stories.tsx, a page story whose play asserts the page structure (the story is the page's test, not a route test). It refuses the reserved page-folder names tests, hooks, state, utils and assets. Layout rule: frontend/.claude/rules/coding-guidelines-react.md.
Data variants
Bind a service with --data <server|client|query> --service <name> --shape <list|detail>. The rule for choosing a variant lives in frontend/.claude/skills/react-code/SKILL.md; the default is server.
server: a serverloader, read withuseLoaderData.client: aclientLoaderand aHydrateFallback. The server renders only theHydrateFallback, so the first load shows its skeleton until the JavaScript loads and theclientLoaderresolves, and the document's title and meta tags are the ones theHydrateFallbackrenders, never values from the loaded data.query: aclientLoaderthat primes the Query cache and aHydrateFallback, with the page readinguseSuspenseQuery. Needs Query installed and the service'squeries.ts; the same first-load and metadata cost asclientapplies.
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 Changed · -2 lines 560343a0e4c8
- 11d ago Changed 1571293e86a2
- 15d ago Changed f6b8bb0fb1c2
- 21d ago Changed · +1 tokens per session 2793ac3c3752
- 23d ago Changed · +1 lines · -1 tokens per session e21ef73a93c0
- 24d ago Changed 9e11499721c2
- 25d ago Changed · +2 lines · -6 tokens per session 49bab31ea762
- 26d ago Changed 7423c474dd05
- 1mo ago Changed · -1 tokens per session f8b9500516ce
- 1mo ago First seen · 26 lines · 94 tokens per session scan A 728acab6fc52
new-route is a skill published in the GitHub repository gaia-react/gaia (26 stars, last pushed 4d ago), licensed MIT. It adds 87 tokens to every session and 699 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
playwright-page-objects
Use when creating page objects or refactoring Playwright E2E tests for better maintainability with Page Object Model patterns.
test-building-blocks
Test building block catalog — typed patterns for Storybook play-function tests, Vitest hook tests, Vitest unit tests, MSW handlers, and test data fixtures. Read the relevant rule file before writing or modifying any test, handler, or fixture. Covers: deciding which kind of test to write, authoring a new test from…
testing
A guide for testing React components with React Testing Library and Vitest. It emphasizes checking interfaces through the way users find and interact with them.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…