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 ezesubu/VERA --skill mobile-perf-doctorgit clone --depth 1 https://github.com/ezesubu/VERAWrote 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/ezesubu/vera/mobile-perf-doctor)<a href="https://agentmods.dev/skills/ezesubu/vera/mobile-perf-doctor"><img src="https://agentmods.dev/badge/skills/ezesubu/vera/mobile-perf-doctor/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/ezesubu/vera/mobile-perf-doctor"><img src="https://agentmods.dev/badge/skills/ezesubu/vera/mobile-perf-doctor.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 | $0.00000 | $0.00606 |
| Opus 5 | $0.00000 | $0.00303 |
| Sonnet 5 | $0.00000 | $0.00121 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
mobile-perf-doctor 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 11d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile / Performance Doctor
VERA ships a mobile and performance doctor: a small set of read-only tools that audit the project for things that hurt — or outright break — a mobile build. Use it proactively whenever the user is about to package for mobile, complains about device crashes, or worries about GPU/shader cost.
When to use which tool
check_mobile_compat— run this BEFORE packaging for mobile. It scans the project's materials via the AssetRegistry and returns an OK-vs-flagged report.find_expensive_materials— run this alongsidecheck_mobile_compatto see the heaviest shaders ranked by cost (instruction + sampler heuristic). Passlimitto control how many (default 10).profile_level— run this to sanity-check the cost of the currently open level: actor/light/static-mesh counts, an approximate triangle total, and obvious red flags (e.g. too many dynamic lights for mobile).
A good pre-package routine: check_mobile_compat → find_expensive_materials →
profile_level, then summarize the risks for the user before they build.
The headline offender: gFur / PCW-GFur_Advanced
On THIS project the gFur / PCW-GFur_Advanced fur shader is a known crash source.
It fails to compile on UE5.7, which leaves a null material, and that null
material dereferences to a SIGSEGV crash on mobile. check_mobile_compat
specifically flags any material whose name matches gFur / PCW-GFur_Advanced.
If it shows up flagged, treat it as a blocker: the material must be replaced or
removed before a mobile package can be trusted.
Honesty about the heuristics
These tools are heuristic, not a certification:
check_mobile_compatflags by name pattern (the strongest, reliable signal for the gFur case) plus reachable instruction/sampler stats. Absence of flags does NOT guarantee mobile safety — it only means nothing matched the known patterns.- Instruction and sampler counts depend on the editor's Python API surface in the
running build; when a stat is unreadable the tools degrade gracefully and say so
(e.g.
instr=?,stats unreachable) rather than crashing. profile_leveltriangle totals are LOD0, static-mesh-actor only, and may be partial if some meshes can't be read; treat the number as an order-of-magnitude signal.
What ships with it
4 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.
- 11d ago First seen · 47 lines · 0 tokens per session scan A d2ade6d1da8c
mobile-perf-doctor is a skill published in the GitHub repository ezesubu/VERA (16 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 606 tokens. 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 2026-08-30.
Other skills, from other repositories
firebase-crashlytics
Use when implementing crash reporting, capturing fatal/non-fatal errors, recording isolate/async exceptions, customizing reports, or uploading obfuscated symbols.
flutter-errors
Use when hitting layout errors (RenderFlex overflow, unbounded constraints, RenderBox not laid out), scroll errors, or setState-during-build errors.
swift-development
You MUST activate this skill when working on Swift projects.
systematic-debugging
Applies a modified Fagan Inspection methodology to resolve persistent bugs and complex issues. Use when several fix or debugging attempts have already failed and a methodical root-cause analysis warranting a Fagan inspection is needed. For first-pass diagnosis of a reproducible bug or regression use…
reframe-voice
Write, rewrite, or review content in the evidence-led reframe voice style. Use when the user explicitly asks to write in "reframe voice" or "reframe style". Do NOT use for general writing tasks.
axiom-networking-diag
Use when debugging connection timeouts, TLS handshake failures, data not arriving, connection drops, performance issues, or proxy/VPN interference - systematic Network.framework diagnostics with production crisis defense.