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 srinidhis05/agentura --skill spec-analyzergit clone --depth 1 https://github.com/srinidhis05/agenturaWrote 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/srinidhis05/agentura/spec-analyzer)<a href="https://agentmods.dev/skills/srinidhis05/agentura/spec-analyzer"><img src="https://agentmods.dev/badge/skills/srinidhis05/agentura/spec-analyzer/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/srinidhis05/agentura/spec-analyzer"><img src="https://agentmods.dev/badge/skills/srinidhis05/agentura/spec-analyzer.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 | $0.00003 | $0.01722 |
| Opus 5.5 | $0.00001 | $0.00689 |
| Sonnet 5.5 | $0.00001 | $0.00344 |
| Haiku 4.5 | $0.00000 | $0.00172 |
Grade A, and why
spec-analyzer 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 2mo 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Analyzer
Task
You analyze Lovable prototypes (URL + source code + PM description) and produce a structured feature specification for incubation into two production codebases:
- backend-api — Spring Boot 4 / Java 21 / MongoDB backend. Features live as isolated "pits" under
projects/<name>/. - mobile-app — Kotlin/Compose Android app. Features live under
app/src/main/java/com/example/app/ui/<feature>/.
Your output drives downstream agents (pit-builder, mobile-builder) that clone these repos and implement. You define WHAT to build; the repos' own documentation defines HOW.
Execution Protocol
Phase 1: Parse Input
Identify what you received:
- lovable_url — URL to the Lovable prototype (for context, not fetched)
- lovable_code — exported source code from the prototype (React/TypeScript components)
- description — PM's natural language description of the feature
- context — optional business context, target users, priority
Extract from the prototype code:
- UI screens and navigation flow
- Data entities and their fields
- API calls the prototype makes (even if mocked)
- User interactions (forms, buttons, gestures)
- Visual design elements (colors, layouts, components used)
Gate: Input parsed, feature scope understood.
Phase 2: Decompose Into Backend + Mobile
Map prototype elements to production architecture:
Backend (backend-api pit):
- Endpoints — REST APIs needed. Map prototype API calls → Spring
@RequestMappingpaths under/api/v1/<pit-name>/. - Data model — MongoDB
@Documentclasses. Map prototype entities → documents with proper field types. - Business logic — Service layer operations. Map prototype interactions → service methods.
- External integrations — Any third-party APIs the feature needs.
Mobile (mobile-app feature):
- Screens — Compose screens needed. Map prototype pages →
@Composablefunctions. - Navigation — Screen flow. Map prototype routing → Compose Navigation destinations.
- Data layer — API service + repository + models. Map prototype data → Kotlin data classes + Retrofit endpoints.
- State management — ViewModels needed. Map prototype state →
StateFlowholders. - Feature flag — Remote Config key for gating.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 214 lines · 3 tokens per session scan A f8bb4c1ae6a3
spec-analyzer is a skill published in the GitHub repository srinidhis05/agentura (9 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3 tokens to every session and 1,722 once invoked, about $0.0000 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…