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/juanmhidalgo/claude-pluginsWrote 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/juanmhidalgo/claude-plugins/backend-to-frontend)<a href="https://agentmods.dev/commands/juanmhidalgo/claude-plugins/backend-to-frontend"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/backend-to-frontend/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/juanmhidalgo/claude-plugins/backend-to-frontend"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/backend-to-frontend.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 | $0.00041 | $0.01340 |
| Opus 5 | $0.00020 | $0.00670 |
| Sonnet 5 | $0.00008 | $0.00268 |
| Haiku 4.5 | $0.00004 | $0.00134 |
Grade A, and why
backend-to-frontend 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 5d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend to Frontend Handoff
Generate a structured prompt that a frontend agent can use to implement changes after backend API modifications.
Context
- Current branch: !
git branch --show-current - Recent commits: !
git log --oneline -5
Target: $ARGUMENTS
<best_practices> @handoff/skills/api-change-documentation/SKILL.md </best_practices>
Instructions
Step 1: Identify API Changes
- If a file or endpoint path is provided, read the relevant files
- Use
git diffto identify recent changes to API endpoints, schemas, or response structures - Look for changes in:
- Route/endpoint definitions
- Request/response schemas
- Validation rules
- Error responses
- Authentication/authorization changes
Step 2: Analyze the Changes
For each changed endpoint, document:
- HTTP method and path
- What changed (new field, removed field, type change, etc.)
- Whether it's a breaking change
- Any new error conditions
Step 3: Generate TypeScript Schema
Convert the updated response/request structures to TypeScript interfaces:
- Use strict typing (no
any) - Include JSDoc comments for non-obvious fields
- Mark optional fields with
? - Include union types for enums
Step 4: Generate Handoff Prompt
Output the following structured prompt that can be given to a frontend agent:
Handoff Prompt Output Format
# Frontend Implementation: [Feature/Change Name]
## Context
[1-2 sentences explaining why this change was made and what business problem it solves]
## Changed Endpoints
### [METHOD] /api/path
**Change type**: [New endpoint | Modified response | Modified request | Deprecated]
**Summary**: [What changed in plain language]
## Updated TypeScript Schema
\`\`\`typescript
// [Filename suggestion, e.g., types/api/users.ts]
interface ResponseType {
// ... generated types
}
\`\`\`
## Migration Guide
### Breaking Changes
- [ ] [List any breaking changes that require immediate attention]
### Non-Breaking Changes
- [ ] [List additive changes that are backwards compatible]
## Implementation Checklist
- [ ] Update API client types
- [ ] Update components consuming this data
- [ ] Handle new error cases
- [ ] Update tests
- [ ] [Any endpoint-specific tasks]
## Edge Cases to Handle
- [Null handling considerations]
- [Empty array vs null distinction]
- [Pagination changes if applicable]
- [Error state changes]
## Notes
[Any additional context the frontend developer should know]
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.
- 5d ago First seen · 181 lines · 41 tokens per session scan A 1110a83c64cd
backend-to-frontend is a command published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 1,340 once invoked, about $0.0002 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 2026-09-03.
Other commands, from other repositories
rpc-client
Generate type-safe RPC client from Hono server routes.
azure-dotnet-webapp:webapp-setup
Interactive setup wizard for ASP.NET Core Web API or Blazor projects on Azure — selects project type, auth, database, and Graph integration; scaffolds the full project structure with compilable stubs; and verifies the build.
integrate
Integrate an API from a product manager's spec into the frontend with full surface mapping, modular SOLID-compliant API layer, and integration testing.
frappe-fullstack
Invoke multiple Frappe agents in parallel for full-stack development - coordinates backend, frontend, and architecture agents for complete feature implementation.
add-seo
Add comprehensive SEO to a page using Next.js 15 Metadata API.
add-table
Create advanced data table component with rich features. Implement column sorting (ascending/descending) with multi-column support. Add pagination with page size selector and jump to page. Implement client-side and server-side filtering. Add column visibility toggle with saved preferences. Implement row selection with…