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 trilwu/secskills --skill testing-thick-clientsgit clone --depth 1 https://github.com/trilwu/secskillsWrote 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/trilwu/secskills/testing-thick-clients)<a href="https://agentmods.dev/skills/trilwu/secskills/testing-thick-clients"><img src="https://agentmods.dev/badge/skills/trilwu/secskills/testing-thick-clients/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/trilwu/secskills/testing-thick-clients"><img src="https://agentmods.dev/badge/skills/trilwu/secskills/testing-thick-clients.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00105 | $0.01755 |
| Opus 5 | $0.00053 | $0.00877 |
| Sonnet 5 | $0.00021 | $0.00351 |
| Haiku 4.5 | $0.00011 | $0.00176 |
Grade A, and why
testing-thick-clients 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Thick Clients
A thick client puts part of the application on the tester's own machine, and that is the whole opportunity: the binary, its config, its memory, and its traffic are all reachable. The recurring failure in these apps is trusting the client — enforcing authorization, hiding functionality, or holding secrets on a box the user controls. The job is to enumerate that surface and show where the trust is misplaced.
When to Use
- Assessing an installed desktop application (.NET/WPF, Java/Swing, Electron, Qt, native Win32) that communicates with a backend
- A fat client where Burp shows nothing because the traffic is not HTTP or not proxy-aware
- A two-tier app that connects directly to a database
- Reviewing local storage, IPC, update integrity, and DLL loading of a desktop app
When NOT to Use
- Browser/web apps and their APIs — use
testing-web-applicationsandtesting-apis; come here only for an installed desktop client. - Electron internals as a JS reversing problem (unpacking
app.asar, deobfuscating the bundle) lean onreversing-obfuscated-javascriptfor the code, and this skill for the app's trust surface. - Pure reverse engineering of the binary with no security-test goal —
analyzing-binaries, oranalyzing-dotnet-assembliesfor managed code. - Mobile apps —
testing-mobile-applications. - Turning a memory-corruption crash into an exploit — that is
exploiting-memory-corruption.
Map the Architecture First
The single most important question is how many tiers the app has, because it changes what a compromised client gets you:
- Two-tier (client → database directly): the client must hold database credentials, and a connection string in config or memory gives you the same direct database access the app has. This is the highest-value finding in a thick client; look for it first.
- Three-tier (client → app server → database): the client talks to an API, and the surface resembles a web test plus the local attack surface below.
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 · 149 lines · 105 tokens per session scan A b28675f1bbfb
testing-thick-clients is a skill published in the GitHub repository trilwu/secskills (137 stars, last pushed 4d ago), licensed MIT. It adds 105 tokens to every session and 1,755 once invoked, about $0.0005 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 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.
fixing-motion-performance
Audit and fix animation performance issues including layout thrashing, compositor properties, scroll-linked motion, and blur effects. Use when animations stutter, transitions jank, or reviewing CSS/JS animation performance.