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 agentmods add skills/multiplex-term/multiplex/build-and-verifynpx skills add multiplex-term/Multiplex --skill build-and-verifygit clone --depth 1 https://github.com/multiplex-term/MultiplexWhat 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 | $0.00176 | $0.02112 |
| Opus 5 | $0.00088 | $0.01056 |
| Sonnet 5 | $0.00035 | $0.00422 |
| Haiku 4.5 | $0.00018 | $0.00211 |
Grade A, and why
build-and-verify 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 2d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build & Verify Multiplex
Multiplex is a SwiftUI SSH terminal for visionOS (primary) and iPadOS, built
around remote tmux. Tools/build.sh is the single entry point for every build/
test/verify task — it encodes the destinations, the shared DerivedData path, and
the headless verification recipe so callers don't reinvent (or subtly break)
them. Prefer it over hand-writing xcodebuild lines.
Architecture and design context live in CLAUDE.md at the repo root — read that
if the task touches app structure, not just the build.
The entry point
Run everything through Tools/build.sh from the repo root:
./Tools/build.sh gen # regenerate the Xcode project (XcodeGen)
./Tools/build.sh build [vos|ipad] # build one platform (default: vos)
./Tools/build.sh test [vos|ipad] # run MultiplexTests unit tests
./Tools/build.sh verify [vos|ipad] # build + install + drive end-to-end
./Tools/build.sh interop # real mosh-server wire/session proof
./Tools/build.sh all # gen + build both platforms + test
vos = visionOS simulator (Apple Vision Pro), ipad = iPad Pro 13-inch (M5).
visionOS is the primary target — default to it unless the task is iPad-specific.
When to regenerate the project first
The .xcodeproj is generated by XcodeGen and git-ignored — never edit it by
hand. Run ./Tools/build.sh gen (or xcodegen generate) after any of:
- editing
project.yml - adding, removing, or renaming source files under
Multiplex/orMultiplexTests/ - changing a vendored package's manifest under
Vendor/
If a build fails with "file not found" for a source you know exists, or a new type is "unresolved", a stale project is the usual cause — regenerate and retry before debugging further.
Building
./Tools/build.sh build vos # or: ipad
Two things that will bite you if you bypass the script:
- Shared DerivedData. Both platforms build into
./DerivedData(matches.gitignore). The build database locks, so never run a visionOS and an iPad build concurrently against it — they collide with a "database is locked" error. Run them in sequence. The script does one platform per invocation for this reason. - First build resolves vendored packages.
Vendor/swift-nio-sshandVendor/SwiftTermare local same-identity overrides (see CLAUDE.md for why). Aftergenor a clean, the first build re-resolves the whole package graph and is slow; subsequent builds are incremental. Don't mistake the slow first build for a hang.
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.
- 2d ago First seen · 182 lines · 176 tokens per session scan A 3104c4567a72
build-and-verify is a skill published in the GitHub repository multiplex-term/Multiplex (10 stars, last pushed 6d ago), licensed Apache-2.0. It adds 176 tokens to every session and 2,112 once invoked, about $0.0009 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
focus-color
Toggle iTerm2 focus tab coloring on or off. Usage: /focus-color.
workflow-audit
Systematic UI workflow auditing for SwiftUI applications. Discovers entry points, traces user flows, detects dead ends and broken promises, audits data wiring, evaluates from user perspective. Triggers: "workflow audit", "audit flows", "find dead ends", "check navigation".
ui-enhancer-radar
Systematic iOS/SwiftUI UI audit with design intent interview, 14-domain analysis (including Color Audit with adaptive Color Profile, iPad Sheet Sizing caller-side audit, Button Hit Region three-factor interaction audit, and Silent Picker menu-presentation audit), element compaction, cross-view consistency checks…
ui-path-radar
UI path tracer for SwiftUI/UIKit apps. 5-layer audit with 34 issue categories and 19 automated checks: discover entry points, trace flows, detect dead ends and broken promises, evaluate UX impact, verify data wiring. Supports targeted trace, diff against previous audits, and handoff to planning skills. Triggers…
capstone-radar
Unified A-F grading and ship/no-ship decisions for the 6-skill radar family (5 companions + capstone). Aggregates handoffs from data-model, ui-path, roundtrip, time-bomb, and ui-enhancer; owns 5 grep-reliable domains; tracks velocity; celebrates improvements. Triggers: "capstone radar", "can I ship", "grade codebase"…
swift-architecture-skill
Swift iOS architecture guidance and playbooks for MVVM, MVI, TCA, Clean Architecture, VIPER, MVP, Coordinator, and Reactive patterns. Use when designing, implementing, refactoring, or reviewing the architecture of a SwiftUI or UIKit feature, module, or codebase.