Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fluttersdk/ainpx agentmods add skills/fluttersdk/ai/fluttersdk-telescopeWrote 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/fluttersdk/ai/fluttersdk-telescope)<a href="https://agentmods.dev/skills/fluttersdk/ai/fluttersdk-telescope"><img src="https://agentmods.dev/badge/skills/fluttersdk/ai/fluttersdk-telescope.svg" alt="Measured on agentmods" 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 | $0.00264 | $0.04934 |
| Opus 5 | $0.00132 | $0.02467 |
| Sonnet 5 | $0.00053 | $0.00987 |
| Haiku 4.5 | $0.00026 | $0.00493 |
Grade A, and why
fluttersdk-telescope 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 7d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fluttersdk_telescope
Passive runtime inspector for Flutter apps, designed for LLM agents. The
running app captures HTTP, logs, exceptions, dumps, in-app events, gate
checks, DB queries, cache ops, and per-frame performance into 10 in-memory
ring buffers. The agent
calls telescope_* MCP tools (or ./bin/fsa telescope:* from a shell) to
read those buffers on demand, without touching the source or attaching
DevTools.
This skill assumes the app already has telescope installed (a
kDebugMode-gated TelescopePlugin.install() in lib/main.dart, the
MCP server in .mcp.json). If not, run
dart run fluttersdk_telescope telescope:install once from the app root,
restart, and verify with ./bin/fsa telescope:tail.
1. Core Laws
-
Telescope is passive, it captures, never drives. Records flow into the 10 ring buffers as the app runs. The agent reads; it does not produce. Pair with
fluttersdk_duskwhen the agent needs to drive the UI (dusk_tap,dusk_type,dusk_navigate) and then read the consequences. Without something exercising the app, the buffers stay empty. -
Two install layers, mind the gap. Raw
TelescopePlugin.install()only wiresLogWatcherplus the VM extensions, plus the opt-inExceptionWatcherandDumpWatcherif the consumer registered them. Magic-stack apps must additionally callMagicTelescopeIntegration.install()afterMagic.init()to populate the HTTP, events, gates, queries, and magic-cache buffers (and to exposependingCountfor dusk's network-idle gate).MagicTelescopeIntegrationships in themagic_devtoolspackage (importpackage:magic_devtools/telescope.dart), not inmagiccore. Whentelescope_requestsreturns{"records": []}on a known-active app, suspect a missing adapter, not a quiet app. The CLI gives the same hint inline:"No HTTP records (register a TelescopeHttpAdapter).","No DB query records (register MagicQueryWatcher).", etc.
What ships with it
5 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.
- 7d ago First seen · 294 lines · 264 tokens per session scan A f93c1ee534ef
fluttersdk-telescope is a skill published in the GitHub repository fluttersdk/ai (2 stars, last pushed 4d ago), licensed MIT. It adds 264 tokens to every session and 4,934 once invoked, about $0.0013 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 skills, from other repositories
performance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
gke-ai-troubleshooting-jobset-interruption
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or…
gke-node-notready
Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node status, or when workloads are evicted or stuck Pending due to node health. Don't…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
comet-hotfix
A quick workflow for fixing an existing bug in Comet, a tool that manages structured code changes. It moves through opening the change, building, checking, and archiving it.