StarNet is a local-first desktop harness for creating AI agents and arranging them in a pixel-art space station whose layout represents their capabilities, permissions, and workflow. It lets people run real model calls and tools through multiple bounded agents, using their own provider keys or accounts and optionally messaging the station through chat services. The catalogue entries are skills that extend or support work performed by StarNet agents.
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 androoAGI/starnet --skill rest-graphql-debuggit clone --depth 1 https://github.com/androoAGI/starnetWrote 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/androoagi/starnet/rest-graphql-debug)<a href="https://agentmods.dev/skills/androoagi/starnet/rest-graphql-debug"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/rest-graphql-debug/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/androoagi/starnet/rest-graphql-debug"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/rest-graphql-debug.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 | $0.00045 | $0.03452 |
| Opus 5.5 | $0.00018 | $0.01381 |
| Sonnet 5.5 | $0.00009 | $0.00690 |
| Haiku 4.5 | $0.00005 | $0.00345 |
Grade A, and why
rest-graphql-debug scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Diagnose REST and GraphQL problems with the station's tools: `web_request` to send the exact request, `shell.exec` with `curl` when you need response headers, TLS details, or timings, and `web_fetch` for the provider's A How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Testing and Debugging
Diagnose REST and GraphQL problems with the station's tools: web_request to send the exact request, shell.exec with curl when you need response headers, TLS details, or timings, and web_fetch for the provider's API docs. Isolate the failing layer before guessing at a fix.
When to use
- An API returns an unexpected status or body.
- Auth fails (401/403 after a token refresh, OAuth, API key).
- A call works in an API client but fails in code.
- Webhook or callback integration debugging.
- Building or reviewing API integration tests.
- Rate limiting or pagination problems.
Skip it for UI rendering, database query tuning, or DNS and firewall infrastructure (escalate those).
Core principle
Isolate the layer, then fix. A 200 OK can hide broken data. A 500 can mask a one-character auth typo. Walk the chain in order; never skip a step.
1. Connectivity → can we reach the host at all?
1.5 Timeouts → slow to connect, or slow to answer?
2. TLS → is the certificate valid and trusted?
3. Auth → are the credentials correct and unexpired?
4. Request format → does the payload match what the server expects?
5. Response parse → does our code accept what came back?
6. Semantics → does the data mean what we assume?
Your instruments
web_request (DISH) sends one request exactly as you specify it and returns the HTTP status and up to about 8,000 characters of the response body. It does NOT return response headers.
- Arguments:
url,method(GET, HEAD, POST, PUT, PATCH, DELETE),headers,body(a string; send JSON as a string, and the Content-Type defaults toapplication/jsonwhen a body is present),multipartfor file uploads. - Authentication without seeing the secret: reference a key stored in TOOLSETS & CONNECTORS → KEYS by its NAME inside a header value, for example
headers: {"Authorization": "Bearer ${ACME_API_TOKEN}"}. The station substitutes the value at send time. Placeholders work in headers only, never in the url or body. For APIs that want the key as a query parameter, useauth: {"key": "ACME_API_TOKEN", "in": "query", "name": "api_key"}. - Never ask the Commander to paste a token into chat. If no stored key fits, ask them to add one in KEYS.
- Each
web_requestcan ask the Commander for approval, so plan requests instead of spraying them.
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.
- 12d ago First seen · 259 lines · 45 tokens per session scan A 35d5805c4a3c
rest-graphql-debug is a skill published in the GitHub repository androoAGI/starnet (1,468 stars, last pushed 3d ago), licensed MIT. It adds 45 tokens to every session and 3,452 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-04.
Other skills, from other repositories
Debug (reproduce -> isolate -> fix)
Systematically diagnose and fix a bug instead of guessing.
tauri-errors-ipc
Use when encountering invoke errors, serialization failures, or IPC-related panics in Tauri 2. Prevents silent type mismatches between Rust and JavaScript and missing Serialize on error types. Covers serialization failures, command not found, argument type mismatches, permission denied, async panics, and thiserror…
rest-graphql-debug
Debug REST/GraphQL APIs: status codes, auth, schemas, repro.
api-integration-architect
Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.
convex-performance-audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…