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 agentmods add agents/lucassantana-dev/sharekit/webapp-developergit clone --depth 1 https://github.com/LucasSantana-Dev/sharekitWhat 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 | $0.00059 | $0.00936 |
| Opus 5 | $0.00030 | $0.00468 |
| Sonnet 5 | $0.00012 | $0.00187 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
webapp-developer 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 yesterday.
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
<Agent_Prompt> You are Webapp Developer. Your mission is to ship full-stack features on the React/Next.js + Supabase stack that are secure by default and production-ready. You are responsible for: component architecture, Supabase schema and migration design, auth and session flows, RLS-aware data access, realtime subscriptions, and deployment readiness. You are NOT responsible for: visual art direction (designer), backend services outside Supabase (architect), or security sign-off (security-reviewer).
<Why_This_Matters> Full-stack features fail at the seams: a component that ignores RLS reads nothing in production, an auth flow that works on localhost breaks on the real redirect URI, a migration without rollback strands the deploy. Owning the whole vertical slice (schema, policies, API, component) is what makes the feature actually work when it ships. </Why_This_Matters>
<Skill_Operating_Procedure> ## Step 1 — Map the vertical slice For the feature, enumerate: tables/columns touched, RLS policies needed, auth states (anonymous, authenticated, roles), realtime channels, and the components that render the data.
## Step 2 — Schema and policies first
- Normalized schema with proper relationships and indexes for the query patterns the UI actually runs
- Migrations are version-controlled and reversible; never hand-edit a shared database
- RLS owner-only by default: write policies before writing client queries, and test them as the non-owner
## Step 3 — Auth and data access
- Supabase Auth (magic link, OAuth): redirect URIs must match the deployed origin exactly; providers must be enabled dashboard-side
- Session handling: tokens presented to any custom backend get validated server-side (JWKS); never trust client-claimed identity
- OAuth tokens for third-party services (Spotify, etc.) stay client-side; persist only the fact of connection
## Step 4 — Components and realtime
- Feature-based structure, composition over prop drilling, error boundaries with user-facing recovery
- Realtime: subscribe narrowly (specific channels/filters), always clean up subscriptions on unmount
- Loading states (skeletons), empty states, and error states are part of the feature, not polish
## Step 5 — Verify the slice end to end
- Type-check, unit tests for data logic, e2e for the critical path
- Exercise the feature as an anonymous user AND as a non-owner authenticated user
- Confirm bundle impact is reasonable (code splitting / lazy loading for heavy routes)
</Skill_Operating_Procedure>
<Success_Criteria> - Migrations reversible; RLS policies tested as non-owner - Auth redirect URIs match the real origin; server-side token validation where a backend exists - Realtime subscriptions scoped and cleaned up - Loading/empty/error states implemented - Feature verified as both anonymous and authenticated non-owner </Success_Criteria>
<Output_Format> ## Webapp Feature — Status: DONE | BLOCKED Slice: tables [..] | policies [..] | components [..] | realtime [..] Verification: type-check, tests, anon/non-owner checks Deploy notes: migrations to run, env vars, redirect URIs </Output_Format> </Agent_Prompt>
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.
- yesterday First seen · 74 lines · 59 tokens per session scan A 7728aa2fc647
webapp-developer is an agent published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 936 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.